Chen, H.[Hong],
Zhang, Y.P.[Yi-Peng],
Wang, X.[Xin],
Duan, X.G.[Xu-Guang],
Zhou, Y.W.[Yu-Wei],
Zhu, W.W.[Wen-Wu],
DisenDreamer: Subject-Driven Text-to-Image Generation With
Sample-Aware Disentangled Tuning,
CirSysVideo(34), No. 8, August 2024, pp. 6860-6873.
IEEE DOI
2408
Noise reduction, Visualization, Tuning, Controllability,
Image synthesis, Training, Diffusion model,
disentangled finetuning
BibRef
Luo, Y.M.[Yi-Min],
Yang, Q.[Qinyu],
Fan, Y.H.[Yu-Heng],
Qi, H.K.[Hai-Kun],
Xia, M.[Menghan],
Measurement Guidance in Diffusion Models:
Insight from Medical Image Synthesis,
PAMI(46), No. 12, December 2024, pp. 7983-7997.
IEEE DOI
2411
Task analysis, Medical diagnostic imaging, Uncertainty,
Image synthesis, Training, Reliability, Data models,
controllable generation
BibRef
Xiao, G.X.[Guang-Xuan],
Yin, T.W.[Tian-Wei],
Freeman, W.T.[William T.],
Durand, F.[Frédo],
Han, S.[Song],
FastComposer: Tuning-Free Multi-subject Image Generation with Localized
Attention,
IJCV(133), No. 3, March 2025, pp. 1175-1194.
Springer DOI
2502
Code:
WWW Link.
BibRef
Marí, R.[Roger],
Redondo, R.[Rafael],
Latent Diffusion Approaches for Conditional Generation of Aerial
Imagery: A Study,
IPOL(15), 2025, pp. 20-31.
DOI Link
2503
BibRef
Ma, H.Y.[Heng-Yuan],
Zhu, X.T.[Xia-Tian],
Feng, J.F.[Jian-Feng],
Zhang, L.[Li],
Preconditioned Score-Based Generative Models,
IJCV(133), No. 7, July 2025, pp. 4837-4863.
Springer DOI
2506
BibRef
Earlier: A1, A4, A2, A3:
Accelerating Score-Based Generative Models with Preconditioned
Diffusion Sampling,
ECCV22(XXIII:1-16).
Springer DOI
2211
BibRef
Xie, J.H.[Jin-Heng],
Li, Y.X.[Yue-Xiang],
Huang, Y.W.[Ya-Wen],
Liu, H.Z.[Hao-Zhe],
Zhang, W.T.[Wen-Tian],
Zheng, Y.F.[Ye-Feng],
Shou, M.Z.[Mike Zheng],
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained
Diffusion,
ICCV23(7418-7427)
IEEE DOI
2401
BibRef
Duan, H.R.[Hao-Ran],
Shao, S.[Shuai],
Zhai, B.[Bing],
Shah, T.[Tejal],
Han, J.G.[Jun-Gong],
Ranjan, R.[Rajiv],
Parameter Efficient Fine-Tuning for Multi-modal Generative Vision
Models with Möbius-Inspired Transformation,
IJCV(133), No. 7, July 2025, pp. 4590-4603.
Springer DOI
2506
BibRef
And:
Correction:
IJCV(133), No. 9, September 2025, pp. 6637-6637.
Springer DOI
2509
BibRef
Wang, B.[Bingyuan],
Chen, Q.F.[Qi-Feng],
Wang, Z.[Zeyu],
Diffusion-Based Visual Art Creation: A Survey and New Perspectives,
Surveys(57), No. 10, May 2025, pp. xx-yy.
DOI Link
2507
Survey, Art Creation.
Survey, Diffusion. AI-generated content, diffusion model, visual art, creativity,
human-AI collaboration
BibRef
Wu, W.J.[Wei-Jia],
Li, Z.[Zhuang],
He, Y.F.[Ye-Fei],
Shou, M.Z.[Mike Zheng],
Shen, C.H.[Chun-Hua],
Cheng, L.[Lele],
Li, Y.[Yan],
Gao, T.T.[Ting-Ting],
Zhang, D.[Di],
Paragraph-to-Image Generation with Information-Enriched Diffusion Model,
IJCV(133), No. 8, August 2025, pp. 5413-5434.
Springer DOI Code:
WWW Link.
2508
Longer descriptions.
BibRef
Hunter, R.[Rosco],
Dudziak, L.[Lukasz],
Abdelfattah, M.S.[Mohamed S.],
Mehrotra, A.[Abhinav],
Bhattacharya, S.[Sourav],
Wen, H.K.[Hong-Kai],
Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models,
IJCV(133), No. 9, September 2025, pp. 6422-6431.
Springer DOI
2509
BibRef
Wei, Y.L.[Yan-Lei],
Zhang, X.L.[Xiao-Lin],
Wang, Y.P.[Yong-Ping],
Wang, J.Y.[Jing-Yu],
Hu, W.J.[Wei-Jian],
Enhancing Transferability via Spectral Alignment and Grad-CAM Guided
Latent Diffusion Models,
SPLetters(32), 2025, pp. 3260-3264.
IEEE DOI
2509
Noise, Discrete cosine transforms, Discrete Fourier transforms,
Diffusion models, Perturbation methods, Image reconstruction, control-VAE
BibRef
Mao, F.Y.[Fang-Yuan],
Mei, J.L.[Ji-Lin],
Lu, S.[Shun],
Liu, F.[Fuyang],
Chen, L.[Liang],
Zhao, F.Z.[Fang-Zhou],
Hu, Y.[Yu],
PID: Physics-Informed Diffusion Model for Infrared Image Generation,
PR(169), 2026, pp. 111816.
Elsevier DOI Code:
WWW Link.
2509
Physical constraints, Diffusion model, Infrared image generation
BibRef
Wu, H.X.[Hao-Xuan],
Po, L.M.[Lai-Man],
Xu, X.[Xuyuan],
Li, K.[Kun],
Liu, Y.Y.[Yu-Yang],
Jiang, Z.[Zeyu],
Comprehensive regional guidance for attention map semantics in
text-to-image diffusion models,
CVIU(260), 2025, pp. 104492.
Elsevier DOI
2510
Diffusion models, Text-to-image generation
BibRef
Huang, Y.S.[Yu-Shi],
Gong, R.[Ruihao],
Liu, X.L.[Xiang-Long],
Liu, J.[Jing],
Li, Y.H.[Yu-Hang],
Lu, J.W.[Ji-Wen],
Tao, D.C.[Da-Cheng],
Temporal Feature Matters: A Framework for Diffusion Model
Quantization,
PAMI(47), No. 10, October 2025, pp. 8823-8837.
IEEE DOI
2510
Diffusion models, Quantization (signal), Maintenance,
Noise reduction, Computational modeling, Training, Calibration,
hardware acceleration
BibRef
Gan, Y.[Yan],
Xiao, X.Y.[Xin-Yao],
Xiang, T.[Tao],
Wu, C.Q.[Cheng-Qian],
Ouyang, D.Q.[De-Qiang],
SFCM-AEG: Source-Free Cross-Modal Adversarial Example Generation,
MultMed(27), 2025, pp. 6262-6272.
IEEE DOI
2510
Semantics, Text to image, Diffusion models, Perturbation methods,
Glass box, Training, Image restoration, Faces, source-free
BibRef
Pan, Y.X.[Yi-Xiang],
Luo, T.[Ting],
Li, Y.F.[Yu-Feng],
Xing, W.P.[Wen-Peng],
Chen, M.J.[Min-Jie],
Han, M.[Meng],
The Safety Illusion? Testing the Boundaries of Concept Removal in
Diffusion Models,
IP(34), 2025, pp. 6823-6837.
IEEE DOI
2511
Diffusion models, Text to image, Semantics, Safety, Robustness,
Perturbation methods, Optimization, Image synthesis, diffusion model
BibRef
Yao, S.Y.[Si-Yue],
Sun, M.J.[Ming-Jie],
Lim, E.G.[Eng Gee],
Yi, R.[Ran],
Zhong, B.J.[Bao-Jiang],
Gabbouj, M.[Moncef],
Crucial-Diff: A Unified Diffusion Model for Crucial Image and
Annotation Synthesis in Data-Scarce Scenarios,
IP(34), 2025, pp. 7024-7036.
IEEE DOI Code:
WWW Link.
2511
Feature extraction, Diffusion models, Data models, Training,
Computational modeling, Annotations, Synthetic data, Accuracy,
diffusion model
BibRef
Liu, Y.P.[Yang-Peng],
Huang, J.J.[Jun-Jian],
Wen, S.P.[Shi-Ping],
He, X.[Xing],
Zhang, W.[Wei],
Feng, Z.[Zhao],
CTIGEN-CDM: Controlled Text-to-Image Generation Using Cropped
Diffusion Models,
CirSysVideo(35), No. 12, December 2025, pp. 11849-11862.
IEEE DOI
2512
Diffusion models, Text to image, Image synthesis,
Computational modeling, Training, Noise reduction, Semantics, cropped model
BibRef
Wang, H.[Haoshen],
Liu, Z.T.[Zhen-Tao],
Sun, K.[Kaicong],
Wang, X.D.[Xiao-Dong],
Shen, D.G.[Ding-Gang],
Cui, Z.M.[Zhi-Ming],
3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable
and High-Quality Medical Image Generation,
MedImg(44), No. 12, December 2025, pp. 4960-4972.
IEEE DOI Code:
WWW Link.
2512
Biomedical imaging, Training, Image reconstruction, Decoding,
Autoencoders, Image coding, Diffusion models, Computed tomography,
noise estimator
BibRef
Wu, M.R.[Ming-Rui],
Huang, O.C.[Ou-Cheng],
Ji, J.Y.[Jia-Yi],
Liu, J.Z.[Jian-Zhuang],
Sun, X.S.[Xiao-Shuai],
Cao, L.J.[Liu-Juan],
Ji, R.R.[Rong-Rong],
TraDiffusion: Trajectory-Based Training-Free Image Generation,
IJCV(133), No. 12, December 2025, pp. 8570-8588.
Springer DOI
2512
BibRef
Li, T.C.[Tian-Cheng],
Luo, W.J.[Wei-Jian],
Chen, Z.Y.[Zhi-Yang],
Ma, L.Y.[Li-Yuan],
Qi, G.J.[Guo-Jun],
Self-Guidance: Boosting Flow and Diffusion Generation on Their Own,
PAMI(48), No. 1, January 2026, pp. 781-791.
IEEE DOI
2512
Diffusion models, Training, Noise level, Diffusion processes, Hands,
Data mining, Costs, Computational modeling, self-guidance
BibRef
Chan, W.I.[Weng Ian],
Santo, H.[Hiroaki],
Matsushita, Y.[Yasuyuki],
Okura, F.[Fumio],
Instance-wise distribution control of text-to-image diffusion models,
PR(172), 2026, pp. 112614.
Elsevier DOI
2601
Text-to-image generation, Diffusion models, Debiasing, Multi-instance generation
BibRef
Cao, P.[Pu],
Zhou, F.[Feng],
Song, Q.[Qing],
Yang, L.[Lu],
Controllable Generation with Text-to-Image Diffusion Models: A Survey,
PAMI(48), No. 4, April 2026, pp. 4771-4791.
IEEE DOI
2603
Survey, Text to Image.
Survey, Diffusion. Diffusion models, Text to image, Noise, Visualization,
Noise reduction, Reviews, Transformers, Vectors, Taxonomy, Surveys,
AIGC
BibRef
Debuysère, S.[Solène],
Trouvé, N.[Nicolas],
Letheule, N.[Nathan],
Lévêque, O.[Olivier],
Colin, E.[Elise],
Quantitative comparison of fine-tuning techniques for pretrained
latent diffusion models in the generation of unseen SAR images,
PandRS(234), 2026, pp. 93-110.
Elsevier DOI
2603
Remote sensing, Synthetic Aperture Radar,
Latent diffusion model, Data augmentation, Multimodal generative models
BibRef
Li, G.[Gang],
Xie, E.[Enze],
Ge, C.J.[Chong-Jian],
Li, X.[Xiang],
Si, L.Y.[Ling-Yu],
Zheng, C.[Changwen],
Li, Z.G.[Zhen-Guo],
S2I-DiT: Unlocking the semantic-to-image transferability by
fine-tuning large diffusion transformer models,
PR(176), 2026, pp. 113158.
Elsevier DOI
2603
Smantic-to-image synthesis, Diffusion transformer models,
Image generation, Cross-task adaptation
BibRef
Mao, Z.D.[Zhen-Dong],
Huang, M.Q.[Meng-Qi],
Lin, Y.J.[Yi-Jing],
Wang, Q.[Quan],
Zhang, L.[Lei],
Zhang, Y.D.[Yong-Dong],
Toward Accurate Image Generation via Dynamic Generative Image
Transformer,
PAMI(48), No. 5, May 2026, pp. 5910-5927.
IEEE DOI
2604
Codes, Encoding, Image coding, Image synthesis, Transformers, Accuracy,
Vector quantization, Image reconstruction, Training, Visualization,
dynamic network
BibRef
Jia, W.N.[Wei-Nan],
Huang, M.Q.[Meng-Qi],
Chen, N.[Nan],
Zhang, L.[Lei],
Mao, Z.D.[Zhen-Dong],
D2iT: Dynamic Diffusion Transformer for Accurate Image Generation,
CVPR25(12860-12870)
IEEE DOI Code:
WWW Link.
2508
Image coding, Codes, Image recognition, Accuracy, Image synthesis,
Scalability, Noise, Diffusion processes, Transformers, dynamic coding
BibRef
Luan, J.S.[Jun-Sheng],
Li, G.Y.[Guang-Yuan],
Zhang, Z.J.[Zhan-Jie],
Zhao, L.[Lei],
Xing, W.[Wei],
IP-Controller: Decomposition and Optimization of Cross-Attention Maps
for Accurate Subject-Driven Text-to-Image Diffusion Generation,
CirSysVideo(36), No. 4, April 2026, pp. 5274-5287.
IEEE DOI
2604
Text to image, Optimization, Context modeling, Semantics, Faces,
Noise reduction, Visualization, Trees (botanical), Surgery,
subject-driven generation
BibRef
Wu, F.X.[Fu-Xiang],
Liu, L.[Liu],
Hao, F.[Fusheng],
Song, C.Q.[Cheng-Qun],
Tao, D.C.[Da-Cheng],
Cheng, J.[Jun],
NoisePO: Efficient Semantic Noise Generation and Ranking for
Diffusion-Based Text-to-Image Synthesis,
IP(35), 2026, pp. 3705-3719.
IEEE DOI
2604
Filtering, Filters, Particle filters, Communication systems,
Telecommunications, Computer networks, IP networks, error propagation
BibRef
Yao, S.Y.[Si-Yue],
Lim, E.G.[Eng Gee],
Yu, S.Y.[Si-Yue],
Xiao, J.[Jimin],
Xu, H.T.[Hao-Tian],
Sun, M.J.[Ming-Jie],
MvP-Diff: Multivariate yet precise diffusion for anomaly images
synthesis and segmentation,
PR(177), 2026, pp. 113294.
Elsevier DOI
2605
Anomaly images synthesis, Dataset generation, Diffusion models
BibRef
Yang, H.Z.[Hong-Zheng],
Li, J.C.L.[Jason Chun-Lok],
Li, K.[Kun],
Ma, W.[Wenao],
Xu, M.J.[Ming-Jie],
Zhao, Y.Z.[Yu-Zhi],
Po, L.M.[Lai-Man],
RSTFA: Efficient Training-Free Human-Preference Alignment via
Rejection Sampling for Text-to-Image Diffusion Models,
IP(35), 2026, pp. 4571-4586.
IEEE DOI
2605
Feedback, Circuits, Integrated circuits,
Videos, computer vision for social good
BibRef
Kang, Y.H.[Yu-Han],
Shi, H.[Hengcan],
Liu, H.[Hao],
Xie, W.Y.[Wei-Ying],
Fang, L.Y.[Le-Yuan],
Bruzzone, L.[Lorenzo],
Glob-Diffusion: A Global Consistent Diffusion Model for Large-Scale
Image Generation,
CirSysVideo(36), No. 5, May 2026, pp. 7005-7019.
IEEE DOI Code:
WWW Link.
2605
Image synthesis, Diffusion models, Semantics, Videos,
Noise reduction, Standards, Coherence, Remote sensing, Noise,
global consistency
BibRef
Li, C.Y.[Chao-Yang],
Wang, X.[Xin],
Zhu, W.W.[Wen-Wu],
Wang, L.Z.[Ling-Zhi],
Hu, N.[Ning],
Liao, Q.[Qing],
Customized Multi-Subject Text-to-Image Generation With Causal Tuning,
CirSysVideo(36), No. 5, May 2026, pp. 7020-7034.
IEEE DOI
2605
Visualization, Interference, Text to image, Noise reduction, Tuning,
Videos, Image synthesis, Dogs, Distortion,
diffusion models
BibRef
Zhao, W.L.[Wen-Liang],
Shi, M.L.[Ming-Lei],
Yu, X.[Xumin],
Qin, Z.[Zengyi],
Zhou, J.[Jie],
Lu, J.W.[Ji-Wen],
FlowTurbo: Accelerating Flow-Based Image Generation Models via
Multi-Stage Refinement,
PAMI(48), No. 7, July 2026, pp. 7550-7563.
IEEE DOI
2606
Diffusion models, Computational modeling, Predictive models,
Image synthesis, Diffusion processes, Trajectory, Noise,
image generation
BibRef
Ding, X.[Xin],
Wang, Y.W.[Yong-Wei],
Zhang, K.[Kao],
Wang, Z.J.[Z. Jane],
CCDM: Continuous Conditional Diffusion Models for Image Generation,
MultMed(28), 2026, pp. 4360-4372.
IEEE DOI
2606
Diffusion models, Diffusion processes, Training, Generators,
Generative adversarial networks, Image denoising,
continuous scalar conditions
BibRef
Chen, L.F.[Li-Feng],
Wang, J.[Jiner],
Pan, Z.[Zihao],
Zhu, B.[Beier],
Yang, X.F.[Xiao-Feng],
Zhang, C.[Chi],
Detail++: Training-Free Detail Enhancer for T2I Diffusion Models,
IP(35), 2026, pp. 5982-5994.
IEEE DOI
2606
Modeling, Text to image, Diffusion models, Noise reduction, Image synthesis,
Layout, Optimization, Text-to-image generation, text-to-image alignment
BibRef
Zou, C.[Chang],
Zheng, S.[Shikang],
Zhang, E.[Evelyn],
Guo, R.[Runlin],
Xu, H.H.[Hao-Hang],
Shi, Z.Y.[Zheng-Yi],
He, C.H.[Cong-Hui],
Hu, X.[Xuming],
Zhang, L.F.[Lin-Feng],
Rethinking Token-Wise Feature Caching: Accelerating Diffusion
Transformers With Dual Feature Caching,
IP(35), 2026, pp. 6211-6220.
IEEE DOI
2606
Modeling, Diffusion models, Text to image, Transformers, Videos,
Costing, Costs, Noise reduction, Diffusion acceleration, feature caching
BibRef
Zhu, L.X.[Ling-Xuan],
Ma, Y.Z.[Yan-Ze],
Wu, J.J.[Jia-Ji],
Fan, Y.B.[Yan-Bo],
Wang, X.B.[Xia-Bing],
Tan, M.Z.[Ming-Zhou],
AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with
Multi-Instance Airplanes,
RS(18), No. 12, 2026, pp. 1940.
DOI Link
2606
BibRef
Huang, Z.[Zemin],
Luo, W.J.[Wei-Jian],
Geng, Z.Y.[Zheng-Yang],
Qi, G.J.[Guo-Jun],
One-Step Diffusion and Flow Distillation Through Implicit Generator
Matching,
PAMI(48), No. 8, August 2026, pp. 9156-9167.
IEEE DOI
2607
Generators, Diffusion models, Vectors, Data models, Noise, Training,
Text to image, Semiconductor device modeling,
image generation
BibRef
Zeng, T.C.[Tian-Chen],
Wang, S.[Sai],
Wu, Y.[Yu],
Du, B.[Bo],
DiffRES: Unleashing Text-to-Image Diffusion Models for Generative
Referring Expression Segmentation Without Information Leakage,
IP(35), 2026, pp. 7222-7232.
IEEE DOI Code:
WWW Link.
2607
Modeling, Renewable Portfolio Standard, Noise reduction, Training,
Image segmentation, Diffusion models, Visualization,
natural language processing
BibRef
Xia, L.X.[Lin-Xuan],
Wu, B.[Boxi],
Yang, X.L.[Xiao-Long],
Wu, T.R.[Tian-Run],
Zhao, Y.[Yibo],
Cai, D.[Deng],
Liu, W.[Wei],
Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented
Diffusion,
IP(35), 2026, pp. 7249-7260.
IEEE DOI
2607
Modeling, Image synthesis, Noise reduction, Measurement,
Diffusion models, Computers, Training, Visualization, diffusion
BibRef
Shentu, J.J.[Jun-Jie],
Watson, M.[Matthew],
Moubayed, N.A.[Noura Al],
AttenCraft: Attention-Based Disentanglement of Multiple Concepts for
Text-to-Image Customization,
MultMed(28), 2026, pp. 6011-6021.
IEEE DOI
2607
Training, Diffusion models, Adaptation models, Image segmentation,
Accuracy, Text to image, Overfitting, Noise measurement,
attention mechanism
BibRef
Guo, Y.Z.[Yu-Ze],
Wang, B.[Bin],
TuckerDreamer: Subject-driven text-to-image generation via
Tucker-based frequency-domain fine-tuning,
IVC(173), 2026, pp. 106088.
Elsevier DOI
2607
Diffusion model, Subject-driven text-to-image generation, Tucker decomposition
BibRef
Qiu, W.M.[Wei-Min],
Wang, J.K.[Jie-Ke],
Gu, Z.N.[Zhi-Ning],
Hu, V.T.[Vincent Tao],
Tang, M.[Meng],
Diversifying Similar Subjects for Text-to-Image Synthesis with
Self-Cross Diffusion Guidance and Reward,
IJCV(134), No. 8, August 2026, pp. 359.
Springer DOI Code:
WWW Link.
2608
BibRef
Earlier: A1, A2, A5, Only:
Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar
Subjects,
CVPR25(23528-23538)
IEEE DOI
2508
Image synthesis, Text to image, Diffusion models, Transformers,
Birds, Reliability, Videos, guidance, similar subjects, diffusion model
BibRef
Yang, S.[Shu],
Ma, H.Z.[Han-Zhi],
Yu, C.[Chengting],
Wang, A.[Aili],
Fu, P.Q.[Peng-Qi],
Li, E.P.[Er-Ping],
SDiT: Scalable and efficient spiking diffusion transformers for image
generation,
PRL(207), 2026, pp. 266-273.
Elsevier DOI
2608
Spiking neural networks, Image generation, Efficient training
BibRef
Geng, X.Y.[Xiao-Yu],
Hui, S.X.[Shuai-Xiong],
Wang, Y.X.[Yu-Xin],
Zhou, J.T.Y.[Joey Tian-Yi],
Wang, Z.[Zheng],
Safe Image Generation via Lightweight Concept Erasure in Diffusion
Models,
IP(35), 2026, pp. 7898-7911.
IEEE DOI
2608
Modeling, Diffusion models, Image processing, Training, Interference,
Matrices, Text to image, Diffusion models,
singular value decomposition
BibRef
Zhang, Y.F.[Yun-Fei],
Wang, J.[Jie],
Huang, Y.[Yan],
Chen, T.Y.[Tian-Yi],
Wong, H.S.[Hau-San],
Wu, S.[Si],
ClassBooth: Boost Class Semantics With Bidirectional Feature Fusion
in Text-to-Image Diffusion Models,
MultMed(28), 2026, pp. 6593-6604.
IEEE DOI
2609
Semantics, Diffusion models, Adaptation models, Decoding, Noise,
Training, Text to image, Computational modeling, Accuracy,
class-specific content
BibRef
Lai, Q.[Qing],
Peng, Z.J.[Zong-Ju],
Chen, F.[Fen],
Zou, W.H.[Wen-Hui],
Chen, W.H.[Wei-Hua],
Quality assessment for DIBR-synthesized images based on strong-weak
geometric structural distortions and global sharpness,
SP:IC(148), 2026, pp. 117622.
Elsevier DOI
2609
Image quality assessment, DIBR-synthesized images,
Global sharpness, Geometric structural distortion, Saliency
BibRef
Sabadin, J.[Jernej],
Tomaševic, D.[Darian],
Meden, B.[Blaž],
Peer, P.[Peter],
Štruc, V.[Vitomir],
IDSync: Improving diffusion models through identity classification,
FG26(1-10)
IEEE DOI Code:
WWW Link.
2609
Faces, Modeling, Training, Noise reduction, Face recognition,
Diffusion models, Timing
BibRef
Chiu, P.Y.[Pin-Yen],
Fang, I.S.[I-Sheng],
Chen, J.C.[Jun-Cheng],
Text Slider: Efficient and Plug-and-Play Continuous Concept Control
for Image/Video Synthesis via LoRA Adapters,
WACV26(613-622)
IEEE DOI Code:
WWW Link.
2609
Improve diffusion models.
LoRa, Text to video, Videos, Modulation, Peer-to-peer computing,
Video equipment, Protocols
BibRef
Weng, J.H.[Ju-Hsuan],
Liao, J.W.[Jia-Wei],
Chou, C.F.[Cheng-Fu],
Chen, J.C.[Jun-Cheng],
M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for
Concept Erasure in Diffusion Models,
WACV26(527-536)
IEEE DOI
2609
To remove harmful or copyrighted material from generated images.
Weapons, Protocols, LoRa,
Location awareness, Media Access Control, evaluation benchmark
BibRef
Zafar, O.[Oz],
Cohen, Y.[Yuval],
Wolf, L.[Lior],
Schwartz, I.[Idan],
Detection-Driven Object Count Optimization for Text-to-Image
Diffusion Models,
WACV26(1885-1894)
IEEE DOI
2609
Circuits, Feedback, Protocols, Amplitude shift keying,
Location awareness, Amplitude modulation
BibRef
Vardhana, K.S.[Korada Sri],
Lolla, S.[Shrikrishna],
Biswas, S.[Soma],
Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models,
WACV26(1221-1230)
IEEE DOI
2609
Product development, Protocols,
Graphical user interfaces, LoRa, Radio access networks,
h-space
BibRef
Park, C.Y.[Chicago Y.],
Hu, Y.Y.[Yu-Yang],
McCann, M.T.[Michael T.],
Garcia-Cardona, C.[Cristina],
Wohlberg, B.[Brendt],
Kamilov, U.S.[Ulugbek S.],
Plug-and-Play Priors as a Score-Based Method,
ICIP25(49-54)
IEEE DOI Code:
WWW Link.
2601
Training, Codes, Inverse problems, Image synthesis, Neural networks,
Imaging, Reconstruction algorithms, Diffusion models, computational imaging
BibRef
Luo, Y.[Yueheng],
Cao, T.W.[Tian-Wei],
Wang, R.[Rui],
Jin, L.[Ling],
Liu, W.D.[Wei-Dong],
Gao, D.H.[Dong-Hui],
Liang, K.M.[Kong-Ming],
Ma, Z.Y.[Zhan-Yu],
A Debiasing Framework For Attribute Binding In Diffusion-Based
Text-To-Image Generation,
ICIP25(1684-1689)
IEEE DOI
2601
Accuracy, Image synthesis, Prevention and mitigation,
Large language models, Semantics, Text to image, Training data, Debiasing
BibRef
Binici, K.[Kuluhan],
Acar, C.[Cihan],
Aggarwal, S.[Shivam],
Liu, S.Y.[Si-Ying],
Mitra, T.[Tulika],
Efficient Text-to-Image Generation: An Adaptive Step Schedule
Controller for Diffusion Models,
ICIP25(355-360)
IEEE DOI
2601
Training, Schedules, Visualization, Adaptation models,
Thresholding (Imaging), Computational modeling, Noise reduction,
efficient AI
BibRef
Lee, S.[Seonho],
Choi, J.[Jiho],
Lim, S.[Seohyun],
Kim, J.[Jiwook],
Shim, H.J.[Hyun-Jung],
Scribble-Guided Diffusion for Training-Free Text-to-Image Generation,
ICIP25(1121-1126)
IEEE DOI
2601
Measurement, Visualization, Accuracy, Shape, Image synthesis,
Diffusion models, Propagation losses, text-to-image generation
BibRef
Chen, B.[Bin],
Wang, H.[Hao],
Zhang, X.L.[Xi-Lin],
Zhu, P.P.[Pin-Pin],
FC-Render: Adaptive Font- and Color-Aware Text Diffusion Model,
ICIP25(2712-2717)
IEEE DOI
2601
Visualization, Adaptation models, Accuracy, Image color analysis,
Text to image, Rendering (computer graphics), Diffusion models, Text Control
BibRef
Chen, Z.Q.[Zhen-Qi],
Yang, Y.F.[Yuan-Fu],
DLSF: Dual-Layer Synergistic Fusion for High-Fidelity Image Synthesis,
MVA25(1-6)
DOI Link Code:
WWW Link.
2512
Visualization, Technological innovation, Smoothing methods,
Image synthesis, Fuses, Machine vision, Semantics,
Software development management
BibRef
Shi, Q.Y.[Qing-Yu],
Qi, L.[Lu],
Wu, J.[Jianzong],
Bai, J.[Jinbin],
Wang, J.B.[Jing-Bo],
Tong, Y.H.[Yun-Hai],
Li, X.T.[Xiang-Tai],
DreamRelation: Bridging Customization and Relation Generation,
CVPR25(15723-15732)
IEEE DOI
2508
Image synthesis, Training data, Text to image, Focusing,
Benchmark testing, Diffusion models, Scenario generation, Engines
BibRef
Ma, X.Y.[Xin-Yin],
Yu, R.[Runpeng],
Liu, S.[Songhua],
Fang, G.[Gongfan],
Wang, X.C.[Xin-Chao],
Diffusion Model is Effectively Its Own Teacher,
CVPR25(12901-12911)
IEEE DOI
2508
Image quality, Computational modeling, Text to image,
Diffusion models, Transformers, Lenses
BibRef
Chu, B.[Beilin],
Xu, X.[Xuan],
Wang, X.[Xin],
Zhang, Y.F.[Yu-Fei],
You, W.[Weike],
Zhou, L.[Linna],
FIRE: Robust Detection of Diffusion-Generated Images via
Frequency-Guided Reconstruction Error,
CVPR25(12830-12839)
IEEE DOI
2508
Training, Image synthesis, Perturbation methods, Diffusion models,
Feature extraction, Robustness, Image reconstruction, Standards
BibRef
Li, S.[Shufan],
Kallidromitis, K.[Konstantinos],
Gokul, A.[Akash],
Liao, Z.[Zichun],
Kato, Y.[Yusuke],
Kozuka, K.[Kazuki],
Grover, A.[Aditya],
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows,
CVPR25(13178-13188)
IEEE DOI Code:
WWW Link.
2508
Radio frequency, Adaptation models, Codes, Attention mechanisms,
Computational modeling, Text to image, Transformers, text-to-image,
diffusion transformer
BibRef
Kim, E.[Eunji],
Kim, S.[Siwon],
Park, M.[Minjun],
Entezari, R.[Rahim],
Yoon, S.[Sungroh],
Rethinking Training for De-biasing Text-to-Image Generation:
Unlocking the Potential of Stable Diffusion,
CVPR25(13361-13370)
IEEE DOI
2508
Training, Image synthesis, Computational modeling, Noise, Semantics,
Text to image, Focusing, Robustness, bias, text-to-image generation, fairness
BibRef
Xia, M.F.[Meng-Fei],
Xue, N.[Nan],
Shen, Y.J.[Yu-Jun],
Yi, R.[Ran],
Gong, T.[Tieliang],
Liu, Y.J.[Yong-Jin],
Rectified Diffusion Guidance for Conditional Generation,
CVPR25(13371-13380)
IEEE DOI Code:
WWW Link.
2508
Closed-form solutions, Codes, Noise reduction,
Toy manufacturing industry, Diffusion processes
BibRef
Ren, J.[Jie],
Chen, K.R.[Kang-Rui],
Cui, Y.Q.[Ying-Qian],
Zeng, S.[Shenglai],
Liu, H.[Hui],
Xing, Y.[Yue],
Tang, J.[Jiliang],
Lyu, L.J.[Ling-Juan],
Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion
Models,
CVPR25(28769-28778)
IEEE DOI
2508
Measurement, Text to image, Benchmark testing, Diffusion models,
Faces, Context modeling
BibRef
Huang, H.Y.[Hua-Yang],
Jin, X.[Xiangye],
Miao, J.X.[Jia-Xu],
Wu, Y.[Yu],
Implicit Bias Injection Attacks against Text-to-Image Diffusion
Models,
CVPR25(28779-28789)
IEEE DOI
2508
Visualization, Image color analysis, Generative AI,
Prevention and mitigation, Semantics, Text to image, generative bias
BibRef
Wang, L.F.[Li-Fu],
Liu, D.Q.[Da-Qing],
Liu, X.C.[Xin-Chen],
He, X.D.[Xiao-Dong],
Scaling Down Text Encoders of Text-to-Image Diffusion Models,
CVPR25(18424-18433)
IEEE DOI Code:
WWW Link.
2508
Image quality, Computational modeling, Semantics, Redundancy,
Natural languages, Text to image, Graphics processing units,
text-representation
BibRef
Wang, C.[Chao],
Fan, H.[Hehe],
Yang, H.[Huichen],
Karimi, S.[Sarvnaz],
Yao, L.[Lina],
Yang, Y.[Yi],
Adapting Text-to-Image Generation with Feature Difference Instruction
for Generic Image Restoration,
CVPR25(23539-23550)
IEEE DOI
2508
Degradation, Training, Adaptation models, Translation, Pipelines,
Noise, Text to image, Feature extraction, Image restoration
BibRef
Liu, Y.P.[Yun-Peng],
Liu, B.X.[Bo-Xiao],
Zhang, Y.[Yi],
Hou, X.Z.[Xing-Zhong],
Song, G.L.[Guang-Lu],
Liu, Y.[Yu],
You, H.[Haihang],
See Further When Clear: Curriculum Consistency Model,
CVPR25(18103-18112)
IEEE DOI
2508
Training, Adaptation models, Schedules, PSNR, Computational modeling,
Noise, Semantics, Text to image, Diffusion models, Pattern matching
BibRef
Lee, B.H.[Byung Hyun],
Lim, S.J.[Sung-Jin],
Chun, S.Y.[Se Young],
Localized Concept Erasure for Text-to-Image Diffusion Models Using
Training-Free Gated Low-Rank Adaptation,
CVPR25(18596-18606)
IEEE DOI Code:
WWW Link.
2508
Training, Art, Codes, Image synthesis, Text to image, Logic gates,
Diffusion models, Robustness, text-to image diffusion models,
gated low-rank adaptation
BibRef
Jang, S.[Sangwon],
Choi, J.S.[June Suk],
Jo, J.[Jaehyeong],
Lee, K.[Kimin],
Hwang, S.J.[Sung Ju],
Silent Branding Attack: Trigger-free Data Poisoning Attack on
Text-to-Image Diffusion Models,
CVPR25(8203-8212)
IEEE DOI Code:
WWW Link.
2508
Measurement, Visualization, Brand management, Text to image,
Training data, Symbols, Diffusion models, Market research, data poisoning
BibRef
Wang, Z.L.[Zi-Lan],
Guo, J.F.[Jun-Feng],
Zhu, J.C.[Jia-Cheng],
Li, Y.M.[Yi-Ming],
Huang, H.[Heng],
Chen, M.[Muhao],
Tu, Z.Z.[Zheng-Zhong],
SleeperMark: Towards Robust Watermark against Fine-Tuning
Text-to-image Diffusion Models,
CVPR25(8213-8224)
IEEE DOI Code:
WWW Link.
2508
Training, Adaptation models, Computational modeling, Semantics,
Text to image, Watermarking, Diffusion models, Robustness,
ownership verification
BibRef
Pan, S.[Shuokai],
Tuzi, G.[Gerti],
Sreeram, S.[Sudarshan],
Gope, D.[Dibakar],
Data-Free Group-Wise Fully Quantized Winograd Convolution via
Learnable Scales,
CVPR25(4091-4100)
IEEE DOI
2508
Quantization (signal), Costs, Accuracy, Convolution, Training data,
Text to image, Diffusion models, Kernel, Usability
BibRef
Dombrowski, M.[Mischa],
Zhang, W.T.[Wei-Tong],
Cechnicka, S.[Sarah],
Reynaud, H.[Hadrien],
Kainz, B.[Bernhard],
Image Generation Diversity Issues and How to Tame Them,
CVPR25(3029-3039)
IEEE DOI Code:
WWW Link.
2508
Measurement, Image quality, Current measurement, Image retrieval,
Training data, Feature extraction, Diffusion models, Data models, Synthetic data
BibRef
Wang, X.[Xi],
Li, H.Z.[Hong-Zhen],
Fang, H.[Heng],
Peng, Y.C.[Yi-Chen],
Xie, H.R.[Hao-Ran],
Yang, X.[Xi],
Li, C.T.[Chun-Tao],
LineArt: A Knowledge-guided Training-free High-quality Appearance
Transfer for Design Drawing with Diffusion Model,
CVPR25(2912-2923)
IEEE DOI Code:
WWW Link.
2508
Training, Visualization, Accuracy, Translation, Image synthesis,
Semantics, Rendering (computer graphics), Painting,
prolines dataset
BibRef
Kwon, M.[Mingi],
Kim, S.S.[Shin Seong],
Jeong, J.[Jaeseok],
Hsiao, Y.T.[Yi Ting],
Uh, Y.[Youngjung],
TCFG: Tangential Damping Classifier-free Guidance,
CVPR25(2620-2629)
IEEE DOI
2508
Manifolds, Image quality, Image synthesis, Refining, Text to image,
Diffusion models, Vectors, Trajectory, Singular value decomposition
BibRef
Wu, B.[Bin],
Shi, W.[Wuxuan],
Wang, J.Q.[Jin-Qiao],
Ye, M.[Mang],
Synthetic Data is an Elegant GIFT for Continual Vision-Language
Models,
CVPR25(2813-2823)
IEEE DOI
2508
Adaptation models, Data privacy, Text to image, Diffusion models,
Data models, Synthetic data, vision-language model
BibRef
Zhang, X.[Xiao],
Jiang, R.X.[Ruo-Xi],
Willett, R.[Rebecca],
Maire, M.[Michael],
Nested Diffusion Models Using Hierarchical Latent Priors,
CVPR25(2502-2512)
IEEE DOI
2508
Image quality, Dimensionality reduction, Visualization,
Image synthesis, Computational modeling, Scalability, Semantics
BibRef
Srivatsan, K.[Koushik],
Shamshad, F.[Fahad],
Naseer, M.[Muzammal],
Patel, V.M.[Vishal M.],
Nandakumar, K.[Karthik],
STEREO: A Two-Stage Framework for Adversarially Robust Concept
Erasing from Text-to-Image Diffusion Models,
CVPR25(23765-23774)
IEEE DOI
2508
Training, Systematics, Text to image, Benchmark testing,
Diffusion models, Robustness, Security, Object recognition, Glass box
BibRef
Miao, B.M.[Bo-Ming],
Li, C.X.[Chun-Xiao],
Wang, X.X.[Xiao-Xiao],
Zhang, A.[Andi],
Sun, R.[Rui],
Wang, Z.Z.[Zi-Zhe],
Zhu, Y.[Yao],
Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image
Synthesis,
CVPR25(23575-23584)
IEEE DOI
2508
Visualization, Semantics, Noise, Text to image, Diffusion processes,
Diffusion models, Question answering (information retrieval),
text-to-image synthesis
BibRef
Cha, S.[Seung_Ju],
Lee, K.[Kwanyoung],
Kim, Y.C.[Ye-Chan],
Oh, H.W.[Hyun-Woo],
Kim, D.J.[Dong-Jin],
VerbDiff: Text-Only Diffusion Models with Enhanced Interaction
Awareness,
CVPR25(8041-8050)
IEEE DOI
2508
Accuracy, Computational modeling, Semantics, Text to image,
Diffusion models, Photorealistic images
BibRef
Li, S.M.[Sen-Mao],
Wang, L.[Lei],
Wang, K.[Kai],
Liu, T.[Tao],
Xie, J.[Jiehang],
van de Weijer, J.[Joost],
Khan, F.S.[Fahad Shahbaz],
Yang, S.Q.[Shi-Qi],
Wang, Y.X.[Ya-Xing],
Yang, J.[Jian],
One-Way Ticket: Time-Independent Unified Encoder for Distilling
Text-to-Image Diffusion Models,
CVPR25(23563-23574)
IEEE DOI Code:
WWW Link.
2508
Image quality, Image synthesis, Computational modeling, Semantics,
Noise, Text to image, Diffusion models, Decoding, Time complexity,
one-step generation
BibRef
Li, Z.J.[Zi-Jie],
Li, H.[Henry],
Shi, Y.C.[Yi-Chun],
Farimani, A.B.[Amir Barati],
Kluger, Y.[Yuval],
Yang, L.J.[Lin-Jie],
Wang, P.[Peng],
Dual Diffusion for Unified Image Generation and Understanding,
CVPR25(2779-2790)
IEEE DOI
2508
Visualization, Maximum likelihood estimation, Image synthesis,
Computational modeling, Text to image, Predictive models,
BibRef
Bernal-Berdun, E.[Edurne],
Serrano, A.[Ana],
Masia, B.[Belen],
Gadelha, M.[Matheus],
Hold-Geoffroy, Y.[Yannick],
Sun, X.[Xin],
Gutierrez, D.[Diego],
PreciseCam: Precise Camera Control for Text-to-Image Generation,
CVPR25(2724-2733)
IEEE DOI
2508
Geometry, Text to image, Cameras, Distortion, Prompt engineering,
Videos, Lenses
BibRef
Parihar, R.[Rishubh],
Agrawal, V.[Vaibhav],
VS, S.[Sachidanand],
Babu, R.V.[R. Venkatesh],
Compass Control: Multi Object Orientation Control for Text-to-Image
Generation,
CVPR25(2791-2801)
IEEE DOI
2508
Training, Solid modeling, Position control, Text to image,
Diffusion models, Compass, Synthetic data, generative models,
3d control
BibRef
Jiang, J.X.[Jia-Xiu],
Zhang, Y.[Yabo],
Feng, K.[Kailai],
Wu, X.H.[Xiao-He],
Li, W.B.[Wen-Bo],
Pei, R.[Renjing],
Li, F.[Fan],
Zuo, W.M.[Wang-Meng],
MC2: Multi-concept Guidance for Customized Multi-concept Generation,
CVPR25(2802-2812)
IEEE DOI Code:
WWW Link.
2508
Adaptation models, Visualization, Computational modeling, Refining,
Text to image, Interference, Optimization
BibRef
Shimoda, W.[Wataru],
Inoue, N.[Naoto],
Haraguchi, D.[Daichi],
Mitani, H.[Hayato],
Uchida, S.[Seiichi],
Yamaguchi, K.[Kota],
Type-R: Automatically Retouching Typos for Text-to-Image Generation,
CVPR25(2745-2754)
IEEE DOI
2508
Image quality, Training, Accuracy, Computational modeling,
Face recognition, Pipelines, Text to image,
graphic design
BibRef
Schusterbauer, J.[Johannes],
Gui, M.[Ming],
Fundel, F.[Frank],
Ommer, B.[Björn],
Diff2Flow: Training Flow Matching Models via Diffusion Model
Alignment,
CVPR25(28347-28357)
IEEE DOI Code:
WWW Link.
2508
Training, Computational modeling,
Biological system modeling, Text to image, Performance gain,
diffusion
BibRef
Han, J.[Jiyeon],
Kwon, D.[Dahee],
Lee, G.[Gayoung],
Kim, J.[Junho],
Choi, J.[Jaesik],
Enhancing Creative Generation on Stable Diffusion-based Models,
CVPR25(28609-28618)
IEEE DOI
2508
Computational modeling, Catalysts, Noise reduction, Text to image,
Diffusion models, Creativity, Optimization, Guidelines,
stable diffusion
BibRef
Sehwag, V.[Vikash],
Kong, X.H.[Xiang-Hao],
Li, J.T.[Jing-Tao],
Spranger, M.[Michael],
Lyu, L.J.[Ling-Juan],
Stretching Each Dollar: Diffusion Training from Scratch on a
Micro-Budget,
CVPR25(28596-28608)
IEEE DOI Code:
WWW Link.
2508
Training, Costs, Biological system modeling,
Computational modeling, Pipelines, Text to image, Transformers,
low-cost ai
BibRef
Lu, Y.H.[Yun-Hong],
Wang, Q.C.[Qi-Chao],
Cao, H.[Hengyuan],
Wang, X.[Xierui],
Xu, X.Y.[Xiao-Yin],
Zhang, M.[Min],
InPO: Inversion Preference Optimization with Reparametrized DDIM for
Efficient Diffusion Model Alignment,
CVPR25(28629-28639)
IEEE DOI
2508
Training, Correlation, Large language models, Text to image,
Focusing, Diffusion models, Data models, Reliability, Optimization
BibRef
Tang, B.D.[Bing-Da],
Zheng, B.Y.[Bo-Yang],
Paul, S.[Sayak],
Xie, S.[Saining],
Exploring the Deep Fusion of Large Language Models and Diffusion
Transformers for Text-to-Image Synthesis,
CVPR25(28586-28595)
IEEE DOI
2508
Training, Uncertainty, Large language models, System performance,
Design methodology, Noise reduction, Text to image, Transformers, Guidelines
BibRef
Zhang, X.X.[Xin-Xi],
Wen, S.[Song],
Han, L.[Ligong],
Juefei-Xu, F.[Felix],
Srivastava, A.[Akash],
Huang, J.Z.[Jun-Zhou],
Pavlovic, V.[Vladimir],
Wang, H.[Hao],
Tao, M.[Molei],
Metaxas, D.N.[Dimitris N.],
SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models,
WACV25(4665-4682)
IEEE DOI
2505
Adaptation models, Computational modeling, Text to image,
Diffusion models, Vectors, Computational efficiency, Matrix decomposition
BibRef
Zeng, Y.[Yan],
Suganuma, M.[Masanori],
Okatani, T.[Takayuki],
Inverting the Generation Process of Denoising Diffusion Implicit Models:
Empirical Evaluation and a Novel Method,
WACV25(4516-4524)
IEEE DOI
2505
Measurement, Accuracy, Image synthesis, Computational modeling,
Noise reduction, Noise, Diffusion models, Image reconstruction, diffusion models
BibRef
Lee, H.[Haeil],
Lee, H.S.[Han-Sang],
Gye, S.[Seoyeon],
Kim, J.[Junmo],
Beta Sampling is All You Need: Efficient Image Generation Strategy
for Diffusion Models Using Stepwise Spectral Analysis,
WACV25(4215-4224)
IEEE DOI
2505
Fourier transforms, Image synthesis, Noise reduction, Focusing,
Diffusion models, Sampling methods, Computational efficiency,
efficient image generation
BibRef
Adaloglou, N.[Nikolas],
Kaiser, T.[Tim],
Michels, F.[Felix],
Kollmann, M.[Markus],
Rethinking Cluster-Conditioned Diffusion Models for Label-Free Image
Synthesis,
WACV25(3603-3613)
IEEE DOI Code:
WWW Link.
2505
Training, Image quality, Visualization, Upper bound, Systematics,
Codes, Image synthesis, Focusing, Diffusion models, image synthesis
BibRef
Theiss, J.[Justin],
Müller, N.[Norman],
Kim, D.[Daeil],
Prakash, A.[Aayush],
Multi-View Image Diffusion via Coordinate Noise and Fourier Attention,
WACV25(4310-4319)
IEEE DOI
2505
Measurement, Time-frequency analysis, Correlation,
Attention mechanisms, Noise, Text to image, Diffusion processes, Videos
BibRef
Li, S.J.[Shi-Jie],
Zanjani, F.G.[Farhad G.],
Yahia, H.B.[Haitam Ben],
Asano, Y.[Yuki],
Gall, J.[Jürgen],
Habibian, A.[Amirhossein],
Valid: Variable-Length Input Diffusion for Novel View Synthesis,
WACV25(2240-2249)
IEEE DOI
2505
Training, Visualization, Costs, Image synthesis, Fuses,
Computational modeling, Diffusion processes, Diffusion models,
diffusion model
BibRef
Garcia, G.M.[Gonzalo Martin],
Zeid, K.A.[Karim Abou],
Schmidt, C.[Christian],
de Geus, D.[Daan],
Hermans, A.[Alexander],
Leibe, B.[Bastian],
Fine-Tuning Image-Conditional Diffusion Models is Easier than you
Think,
WACV25(753-762)
IEEE DOI
2505
Training, Geometry, Protocols, Image synthesis,
Computational modeling, Depth measurement, Pipelines, Estimation,
Reliability
BibRef
Cui, Q.P.[Qin-Peng],
Zhang, X.[Xinyi],
Bao, Q.Q.[Qi-Qi],
Liao, Q.M.[Qing-Min],
Elucidating the Solution Space of Extended Reverse-Time SDE for
Diffusion Models,
WACV25(243-252)
IEEE DOI Code:
WWW Link.
2505
Visualization, Codes, Buildings, Stochastic processes,
Differential equations, Diffusion models
BibRef
Xu, K.[Katherine],
Zhang, L.Z.[Ling-Zhi],
Shi, J.B.[Jian-Bo],
Detecting Origin Attribution for Text-to-Image Diffusion Models,
WACV25(8775-8785)
IEEE DOI
2505
Training, Visualization, Image forensics, Accuracy,
Image recognition, Image synthesis, Text to image, fake image detection
BibRef
Dutt, R.[Raman],
Bohdal, O.[Ondrej],
Sanchez, P.[Pedro],
Tsaftaris, S.A.[Sotirios A.],
Hospedales, T.[Timothy],
MemControl: Mitigating Memorization in Diffusion Models via Automated
Parameter Selection,
WACV25(4491-4501)
IEEE DOI
2505
Uniform resource locators, Measurement, Law, Image synthesis,
Prevention and mitigation, Training data, Text to image,
medical image analysis
BibRef
Xu, K.[Katherine],
Zhang, L.Z.[Ling-Zhi],
Shi, J.B.[Jian-Bo],
Good Seed Makes a Good Crop: Discovering Secret Seeds in
Text-to-Image Diffusion Models,
WACV25(3024-3034)
IEEE DOI
2505
Visualization, Accuracy, Image synthesis, Noise, Text to image,
Diffusion processes, Crops, Gray-scale, Diffusion models, seeds
BibRef
Jena, R.[Rohit],
Taghibakhshi, A.[Ali],
Jain, S.[Sahil],
Shen, G.[Gerald],
Tajbakhsh, N.[Nima],
Vahdat, A.[Arash],
Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image
Diffusion Models,
WACV25(232-242)
IEEE DOI
2505
Measurement, Training, Annealing, Monte Carlo methods, Noise,
Text to image, Diffusion models, Data models, Computer crime,
text-to-image alignment
BibRef
Kang, W.J.[Won-Jun],
Galim, K.[Kevin],
Koo, H.I.[Hyung Il],
Cho, N.I.[Nam Ik],
Counting Guidance for High Fidelity Text-to-Image Synthesis,
WACV25(899-908)
IEEE DOI
2505
Knowledge engineering, Noise, Noise reduction, Text to image, Diffusion models,
Tuning, generative models, diffusion models, text-to-image generation
BibRef
Sun, Z.C.[Zhi-Cheng],
Jiang, Y.[Yuan],
Qin, Z.[Zihao],
Deng, Y.C.[Yan-Cong],
Clip2Sam: Enhanced End-to-End Text-to-Image Segmentation and Image
Diffusion System,
ICIVC24(169-176)
IEEE DOI
2503
Image segmentation, Computational modeling, Semantics, Text to image,
Surgery, Diffusion models, Robustness, Standards, Segmentation
BibRef
Voynov, A.[Andrey],
Hertz, A.[Amir],
Arar, M.[Moab],
Fruchter, S.[Shlomi],
Cohen-Or, D.[Daniel],
Curved Diffusion: A Generative Model with Optical Geometry Control,
ECCV24(LXXVII: 149-164).
Springer DOI
2412
BibRef
Chen, J.S.[Jun-Song],
Ge, C.J.[Chong-Jian],
Xie, E.[Enze],
Wu, Y.[Yue],
Yao, L.W.[Le-Wei],
Ren, X.Z.[Xiao-Zhe],
Wang, Z.[Zhongdao],
Luo, P.[Ping],
Lu, H.C.[Hu-Chuan],
Li, Z.G.[Zhen-Guo],
Pixart-sigma: Weak-to-strong Training of Diffusion Transformer for 4k
Text-to-image Generation,
ECCV24(XXXII: 74-91).
Springer DOI
2412
BibRef
Um, S.[Soobin],
Ye, J.C.[Jong Chul],
Self-guided Generation of Minority Samples Using Diffusion Models,
ECCV24(LXVIII: 414-430).
Springer DOI
2412
Code:
WWW Link.
BibRef
Mukhopadhyay, S.[Soumik],
Gwilliam, M.[Matthew],
Yamaguchi, Y.[Yosuke],
Agarwal, V.[Vatsal],
Padmanabhan, N.[Namitha],
Swaminathan, A.[Archana],
Zhou, T.Y.[Tian-Yi],
Ohya, J.[Jun],
Shrivastava, A.[Abhinav],
Do Text-free Diffusion Models Learn Discriminative Visual
Representations?,
ECCV24(LX: 253-272).
Springer DOI
2412
Project:
WWW Link. Code:
WWW Link.
BibRef
Wang, J.Y.[Jia-Yi],
Laube, K.A.[Kevin Alexander],
Li, Y.M.[Yu-Meng],
Metzen, J.H.[Jan Hendrik],
Cheng, S.I.[Shin-I],
Borges, J.[Julio],
Khoreva, A.[Anna],
Label-free Neural Semantic Image Synthesis,
ECCV24(LIII: 391-407).
Springer DOI
2412
BibRef
Xu, C.[Chen],
Song, T.[Tianhui],
Feng, W.X.[Wei-Xin],
Li, X.B.[Xu-Bin],
Ge, T.[Tiezheng],
Zheng, B.[Bo],
Wang, L.M.[Li-Min],
Accelerating Image Generation with Sub-path Linear Approximation Model,
ECCV24(LIII: 323-339).
Springer DOI
2412
BibRef
Garibi, D.[Daniel],
Patashnik, O.[Or],
Voynov, A.[Andrey],
Averbuch-Elor, H.[Hadar],
Cohen-Or, D.[Daniel],
Renoise: Real Image Inversion Through Iterative Noising,
ECCV24(XIV: 395-413).
Springer DOI
2412
BibRef
Cao, Y.[Yu],
Gong, S.G.[Shao-Gang],
Few-shot Image Generation by Conditional Relaxing Diffusion Inversion,
ECCV24(LXXXIV: 20-37).
Springer DOI
2412
BibRef
Huang, R.[Runhui],
Cai, K.X.[Kai-Xin],
Han, J.H.[Jian-Hua],
Liang, X.D.[Xiao-Dan],
Pei, R.[Renjing],
Lu, G.S.[Guan-Song],
Xu, S.[Songcen],
Zhang, W.[Wei],
Xu, H.[Hang],
Layerdiff: Exploring Text-guided Multi-layered Composable Image
Synthesis via Layer-collaborative Diffusion Model,
ECCV24(LXXVI: 144-160).
Springer DOI
2412
BibRef
Brokman, J.[Jonathan],
Hofman, O.[Omer],
Vainshtein, R.[Roman],
Giloni, A.[Amit],
Shimizu, T.[Toshiya],
Singh, I.[Inderjeet],
Rachmil, O.[Oren],
Zolfi, A.[Alon],
Shabtai, A.[Asaf],
Unno, Y.[Yuki],
Kojima, H.[Hisashi],
Montrage: Monitoring Training for Attribution of Generative Diffusion
Models,
ECCV24(LXXV: 1-17).
Springer DOI
2412
BibRef
Desai, A.[Alakh],
Vasconcelos, N.M.[Nuno M.],
Improving Image Synthesis with Diffusion-negative Sampling,
ECCV24(LIII: 199-214).
Springer DOI
2412
BibRef
Zhang, M.Y.[Man-Yuan],
Song, G.L.[Guang-Lu],
Shi, X.Y.[Xiao-Yu],
Liu, Y.[Yu],
Li, H.S.[Hong-Sheng],
Three Things We Need to Know About Transferring Stable Diffusion to
Visual Dense Prediction Tasks,
ECCV24(XLII: 128-145).
Springer DOI
2412
BibRef
Guan, S.[Shanyan],
Ge, Y.H.[Yan-Hao],
Tai, Y.[Ying],
Yang, J.[Jian],
Li, W.[Wei],
You, M.Y.[Ming-Yu],
Hybridbooth: Hybrid Prompt Inversion for Efficient Subject-driven
Generation,
ECCV24(IX: 403-419).
Springer DOI
2412
BibRef
Li, M.[Ming],
Yang, T.[Taojiannan],
Kuang, H.F.[Hua-Feng],
Wu, J.[Jie],
Wang, Z.N.[Zhao-Ning],
Xiao, X.F.[Xue-Feng],
Chen, C.[Chen],
Controlnet++: Improving Conditional Controls with Efficient Consistency
Feedback,
ECCV24(VII: 129-147).
Springer DOI
2412
Project:
WWW Link.
BibRef
Ning, W.X.[Wen-Xin],
Chang, D.L.[Dong-Liang],
Tong, Y.J.[Yu-Jun],
He, Z.J.[Zhong-Jiang],
Liang, K.M.[Kong-Ming],
Ma, Z.Y.[Zhan-Yu],
Hierarchical Prompting for Diffusion Classifiers,
ACCV24(VIII: 297-314).
Springer DOI
2412
Code:
WWW Link.
BibRef
Najdenkoska, I.[Ivona],
Sinha, A.[Animesh],
Dubey, A.[Abhimanyu],
Mahajan, D.[Dhruv],
Ramanathan, V.[Vignesh],
Radenovic, F.[Filip],
Context Diffusion: In-context Aware Image Generation,
ECCV24(LXXVII: 375-391).
Springer DOI
2412
BibRef
Ma, N.[Nanye],
Goldstein, M.[Mark],
Albergo, M.S.[Michael S.],
Boffi, N.M.[Nicholas M.],
Vanden-Eijnden, E.[Eric],
Xie, S.[Saining],
SIT: Exploring Flow and Diffusion-based Generative Models with Scalable
Interpolant Transformers,
ECCV24(LXXVII: 23-40).
Springer DOI
2412
BibRef
Yu, Z.M.[Zheng-Ming],
Dou, Z.Y.[Zhi-Yang],
Long, X.X.[Xiao-Xiao],
Lin, C.[Cheng],
Li, Z.K.[Ze-Kun],
Liu, Y.[Yuan],
Müller, N.[Norman],
Komura, T.[Taku],
Habermann, M.[Marc],
Theobalt, C.[Christian],
Li, X.[Xin],
Wang, W.P.[Wen-Ping],
SURF-D: Generating High-quality Surfaces of Arbitrary Topologies Using
Diffusion Models,
ECCV24(XXXIX: 419-438).
Springer DOI
2412
BibRef
Somepalli, G.[Gowthami],
Gupta, A.[Anubhav],
Gupta, K.[Kamal],
Palta, S.[Shramay],
Goldblum, M.[Micah],
Geiping, J.[Jonas],
Shrivastava, A.[Abhinav],
Goldstein, T.[Tom],
Investigating Style Similarity in Diffusion Models,
ECCV24(LXVI: 143-160).
Springer DOI
2412
BibRef
Qi, Z.[Zipeng],
Huang, G.X.[Guo-Xi],
Liu, C.Y.[Chen-Yang],
Ye, F.[Fei],
Layered Rendering Diffusion Model for Controllable Zero-Shot Image
Synthesis,
ECCV24(LXVI: 426-443).
Springer DOI
2412
BibRef
Ju, X.[Xuan],
Liu, X.[Xian],
Wang, X.T.[Xin-Tao],
Bian, Y.X.[Yu-Xuan],
Shan, Y.[Ying],
Xu, Q.[Qiang],
Brushnet: A Plug-and-play Image Inpainting Model with Decomposed
Dual-branch Diffusion,
ECCV24(XX: 150-168).
Springer DOI
2412
BibRef
Lin, C.H.[Chieh Hubert],
Kim, C.[Changil],
Huang, J.B.[Jia-Bin],
Li, Q.[Qinbo],
Ma, C.Y.[Chih-Yao],
Kopf, J.[Johannes],
Yang, M.H.[Ming-Hsuan],
Tseng, H.Y.[Hung-Yu],
Taming Latent Diffusion Model for Neural Radiance Field Inpainting,
ECCV24(III: 149-165).
Springer DOI
2412
BibRef
Gao, H.A.[Huan-Ang],
Gao, M.J.[Ming-Ju],
Li, J.[Jiaju],
Li, W.[Wenyi],
Zhi, R.[Rong],
Tang, H.[Hao],
Zhao, H.[Hao],
SCP-Diff: Spatial-categorical Joint Prior for Diffusion Based Semantic
Image Synthesis,
ECCV24(XXXII: 37-54).
Springer DOI
2412
BibRef
Le, M.Q.[Minh-Quan],
Graikos, A.[Alexandros],
Yellapragada, S.[Srikar],
Gupta, R.[Rajarsi],
Saltz, J.[Joel],
Samaras, D.[Dimitris],
inf-brush: Controllable Large Image Synthesis with Diffusion Models in
Infinite Dimensions,
ECCV24(XXXII: 385-401).
Springer DOI
2412
BibRef
Gong, C.[Chao],
Chen, K.[Kai],
Wei, Z.P.[Zhi-Peng],
Chen, J.J.[Jing-Jing],
Jiang, Y.G.[Yu-Gang],
Reliable and Efficient Concept Erasure of Text-to-image Diffusion
Models,
ECCV24(LIII: 73-88).
Springer DOI
2412
BibRef
Luo, J.J.[Jian-Jie],
Chen, J.W.[Jing-Wen],
Li, Y.[Yehao],
Pan, Y.W.[Ying-Wei],
Feng, J.L.[Jian-Lin],
Chao, H.Y.[Hong-Yang],
Yao, T.[Ting],
Unleashing Text-to-image Diffusion Prior for Zero-shot Image Captioning,
ECCV24(LVII: 237-254).
Springer DOI
2412
BibRef
Lu, G.S.[Guan-Song],
Guo, Y.F.[Yuan-Fan],
Han, J.H.[Jian-Hua],
Niu, M.Z.[Min-Zhe],
Zeng, Y.H.[Yi-Han],
Xu, S.[Songcen],
Huang, Z.Y.[Ze-Yi],
Zhong, Z.[Zhao],
Zhang, W.[Wei],
Xu, H.[Hang],
Pangu-draw: Advancing Resource-efficient Text-to-image Synthesis with
Time-decoupled Training and Reusable Coop-diffusion,
ECCV24(XLV: 159-176).
Springer DOI
2412
BibRef
Huang, C.P.[Chi-Pin],
Chang, K.P.[Kai-Po],
Tsai, C.T.[Chung-Ting],
Lai, Y.H.[Yung-Hsuan],
Yang, F.E.[Fu-En],
Wang, Y.C.A.F.[Yu-Chi-Ang Frank],
Receler: Reliable Concept Erasing of Text-to-image Diffusion Models via
Lightweight Erasers,
ECCV24(XL: 360-376).
Springer DOI
2412
BibRef
Zhang, Y.[Yasi],
Yu, P.Y.[Pei-Yu],
Wu, Y.N.[Ying Nian],
Object-conditioned Energy-based Attention Map Alignment in
Text-to-image Diffusion Models,
ECCV24(XLII: 55-71).
Springer DOI
2412
BibRef
Chai, W.L.[Wei-Long],
Zheng, D.D.[Dan-Dan],
Cao, J.J.[Jia-Jiong],
Chen, Z.Q.[Zhi-Quan],
Wang, C.B.[Chang-Bao],
Ma, C.G.[Chen-Guang],
Speedupnet: A Plug-and-play Adapter Network for Accelerating
Text-to-image Diffusion Models,
ECCV24(XLIII: 181-196).
Springer DOI
2412
BibRef
Zhang, Y.[Yi],
Tang, Y.[Yun],
Ruan, W.J.[Wen-Jie],
Huang, X.W.[Xiao-Wei],
Khastgir, S.[Siddartha],
Jennings, P.[Paul],
Zhao, X.Y.[Xing-Yu],
Protip: Probabilistic Robustness Verification on Text-to-image
Diffusion Models Against Stochastic Perturbation,
ECCV24(XXXII: 455-472).
Springer DOI
2412
BibRef
Nair, N.G.[Nithin Gopalakrishnan],
Valanarasu, J.M.J.[Jeya Maria Jose],
Patel, V.M.[Vishal M.],
Maxfusion: Plug&play Multi-modal Generation in Text-to-Image Diffusion
Models,
ECCV24(XXXVIII: 93-110).
Springer DOI
2412
BibRef
Zhang, Z.B.[Zheng-Bo],
Xu, L.[Li],
Peng, D.[Duo],
Rahmani, H.[Hossein],
Liu, J.[Jun],
Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers,
ECCV24(XXVIII: 319-337).
Springer DOI
2412
BibRef
Kong, H.Y.[Han-Yang],
Lian, D.Z.[Dong-Ze],
Mi, M.B.[Michael Bi],
Wang, X.C.[Xin-Chao],
Dreamdrone: Text-to-image Diffusion Models Are Zero-shot Perpetual View
Generators,
ECCV24(XIII: 324-341).
Springer DOI
2412
BibRef
Gao, Y.[Yi],
Psg-adapter: Controllable Planning Scene Graph for Improving
Text-to-image Diffusion,
ACCV24(V: 205-221).
Springer DOI
2412
BibRef
Gupta, P.[Parul],
Hayat, M.[Munawar],
Dhall, A.[Abhinav],
Do, T.T.[Thanh-Toan],
Conditional Distribution Modelling for Few-shot Image Synthesis with
Diffusion Models,
ACCV24(V: 3-20).
Springer DOI
2412
BibRef
Ren, J.[Jie],
Li, Y.X.[Ya-Xin],
Zeng, S.L.[Sheng-Lai],
Xu, H.[Han],
Lyu, L.J.[Ling-Juan],
Xing, Y.[Yue],
Tang, J.[Jiliang],
Unveiling and Mitigating Memorization in Text-to-image Diffusion Models
Through Cross Attention,
ECCV24(LXXVII: 340-356).
Springer DOI
2412
BibRef
Zheng, W.[Wendi],
Teng, J.Y.[Jia-Yan],
Yang, Z.[Zhuoyi],
Wang, W.H.[Wei-Han],
Chen, J.[Jidong],
Gu, X.T.[Xiao-Tao],
Dong, Y.X.[Yu-Xiao],
Ding, M.[Ming],
Tang, J.[Jie],
Cogview3: Finer and Faster Text-to-image Generation via Relay Diffusion,
ECCV24(LXXVII: 1-22).
Springer DOI
2412
BibRef
Zhao, J.[Juntu],
Deng, J.Y.[Jun-Yu],
Ye, Y.X.[Yi-Xin],
Li, C.X.[Chong-Xuan],
Deng, Z.J.[Zhi-Jie],
Wang, D.[Dequan],
Lost in Translation: Latent Concept Misalignment in Text-to-image
Diffusion Models,
ECCV24(LXIX: 318-333).
Springer DOI
2412
BibRef
Ma, J.[Jian],
Chen, C.[Chen],
Xie, Q.S.[Qing-Song],
Lu, H.N.[Hao-Nan],
Pea-diffusion: Parameter-efficient Adapter with Knowledge Distillation
in Non-english Text-to-image Generation,
ECCV24(LXVIII: 89-105).
Springer DOI
2412
BibRef
Kim, S.[Sanghyun],
Jung, S.[Seohyeon],
Kim, B.[Balhae],
Choi, M.[Moonseok],
Shin, J.[Jinwoo],
Lee, J.H.[Ju-Ho],
Safeguard Text-to-image Diffusion Models with Human Feedback Inversion,
ECCV24(LXVII: 128-145).
Springer DOI
2412
BibRef
Biggs, B.[Benjamin],
Seshadri, A.[Arjun],
Zou, Y.[Yang],
Jain, A.[Achin],
Golatkar, A.[Aditya],
Xie, Y.S.[Yu-Sheng],
Achille, A.[Alessandro],
Swaminathan, A.[Ashwin],
Soatto, S.[Stefano],
Diffusion Soup: Model Merging for Text-to-image Diffusion Models,
ECCV24(LXIII: 257-274).
Springer DOI
2412
BibRef
Zhao, Y.[Yang],
Xu, Y.[Yanwu],
Xiao, Z.S.[Zhi-Sheng],
Jia, H.L.[Hao-Lin],
Hou, T.B.[Ting-Bo],
Mobilediffusion: Instant Text-to-image Generation on Mobile Devices,
ECCV24(LXII: 225-242).
Springer DOI
2412
BibRef
Zhang, Y.[Yang],
Tzun, T.T.[Teoh Tze],
Hern, L.W.[Lim Wei],
Kawaguchi, K.[Kenji],
Enhancing Semantic Fidelity in Text-to-image Synthesis: Attention
Regulation in Diffusion Models,
ECCV24(LXXXVI: 70-86).
Springer DOI
2412
BibRef
Wang, Z.Q.[Zhong-Qi],
Zhang, J.[Jie],
Shan, S.G.[Shi-Guang],
Chen, X.L.[Xi-Lin],
T2ishield: Defending Against Backdoors on Text-to-image Diffusion
Models,
ECCV24(LXXXV: 107-124).
Springer DOI
2412
BibRef
Kim, C.[Changhoon],
Min, K.[Kyle],
Yang, Y.Z.[Ye-Zhou],
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-image
Diffusion Model,
ECCV24(LXXXIII: 461-478).
Springer DOI
2412
BibRef
Wu, X.S.[Xiao-Shi],
Hao, Y.M.[Yi-Ming],
Zhang, M.Y.[Man-Yuan],
Sun, K.Q.[Ke-Qiang],
Huang, Z.Y.[Zhao-Yang],
Song, G.L.[Guang-Lu],
Liu, Y.[Yu],
Li, H.S.[Hong-Sheng],
Deep Reward Supervisions for Tuning Text-to-image Diffusion Models,
ECCV24(LXXXIII: 108-124).
Springer DOI
2412
BibRef
Choi, D.W.[Dae-Won],
Jeong, J.[Jongheon],
Jang, H.[Huiwon],
Shin, J.[Jinwoo],
Adversarial Robustification via Text-to-image Diffusion Models,
ECCV24(LXXXI: 158-177).
Springer DOI
2412
BibRef
Zavadski, D.[Denis],
Feiden, J.F.[Johann-Friedrich],
Rother, C.[Carsten],
Controlnet-xs: Rethinking the Control of Text-to-image Diffusion Models
as Feedback-control Systems,
ECCV24(LXXXVIII: 343-362).
Springer DOI
2412
BibRef
Maung-Maung, A.P.[April-Pyone],
Nguyen, H.H.[Huy H.],
Kiya, H.[Hitoshi],
Echizen, I.[Isao],
Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious
Feature Generation,
ICIP24(3910-3916)
IEEE DOI
2411
Text to image, Flowering plants, Diffusion models,
Feature extraction, Information filters, Internet, Testing, finetuning
BibRef
Karras, T.[Tero],
Aittala, M.[Miika],
Lehtinen, J.[Jaakko],
Hellsten, J.[Janne],
Aila, T.[Timo],
Laine, S.[Samuli],
Analyzing and Improving the Training Dynamics of Diffusion Models,
CVPR24(24174-24184)
IEEE DOI
2410
Training, Systematics, Costs, Image synthesis, Computer architecture,
Network architecture
BibRef
Li, J.[Jing],
Wang, Z.[Zigan],
Li, J.L.[Jin-Liang],
AdvDenoise: Fast Generation Framework of Universal and Robust
Adversarial Patches Using Denoise,
SAIAD24(3481-3490)
IEEE DOI Code:
WWW Link.
2410
Visualization, Computational modeling, Noise reduction,
Diffusion models, Transformers, Robustness
BibRef
Tang, S.[Siao],
Wang, X.[Xin],
Chen, H.[Hong],
Guan, C.[Chaoyu],
Wu, Z.[Zewen],
Tang, Y.S.[Yan-Song],
Zhu, W.W.[Wen-Wu],
Post-training Quantization with Progressive Calibration and Activation
Relaxing for Text-to-image Diffusion Models,
ECCV24(LVI: 404-420).
Springer DOI
2412
BibRef
Wang, C.Y.[Chang-Yuan],
Wang, Z.W.[Zi-Wei],
Xu, X.W.[Xiu-Wei],
Tang, Y.S.[Yan-Song],
Zhou, J.[Jie],
Lu, J.W.[Ji-Wen],
Towards Accurate Post-Training Quantization for Diffusion Models,
CVPR24(16026-16035)
IEEE DOI Code:
WWW Link.
2410
Quantization (signal), Risk minimization, Accuracy, Tensors,
Image synthesis, Diffusion models, Minimization, diffusion model,
network quantization
BibRef
Islam, K.[Khawar],
Zaheer, M.Z.[Muhammad Zaigham],
Mahmood, A.[Arif],
Nandakumar, K.[Karthik],
Diffusemix: Label-Preserving Data Augmentation with Diffusion Models,
CVPR24(27611-27620)
IEEE DOI Code:
WWW Link.
2410
Training, Performance gain, Diffusion models, Data augmentation,
Robustness, Image augmentation, Fractals, data augmentation, cutmix
BibRef
Qian, Y.R.[Yu-Rui],
Cai, Q.[Qi],
Pan, Y.W.[Ying-Wei],
Li, Y.[Yehao],
Yao, T.[Ting],
Sun, Q.[Qibin],
Mei, T.[Tao],
Boosting Diffusion Models with Moving Average Sampling in Frequency
Domain,
CVPR24(8911-8920)
IEEE DOI
2410
Schedules, Image synthesis, Frequency-domain analysis,
Noise reduction, Diffusion processes, Diffusion models, image generation
BibRef
Yang, K.[Kai],
Tao, J.[Jian],
Lyu, J.[Jiafei],
Ge, C.J.[Chun-Jiang],
Chen, J.X.[Jia-Xin],
Shen, W.H.[Wei-Han],
Zhu, X.L.[Xiao-Long],
Li, X.[Xiu],
Using Human Feedback to Fine-tune Diffusion Models without Any Reward
Model,
CVPR24(8941-8951)
IEEE DOI Code:
WWW Link.
2410
Training, Analytical models, Image coding, Computational modeling,
Noise reduction, Graphics processing units, Diffusion models,
Human feedback
BibRef
Zhou, Z.Y.[Zhen-Yu],
Chen, D.[Defang],
Wang, C.[Can],
Chen, C.[Chun],
Fast ODE-based Sampling for Diffusion Models in Around 5 Steps,
CVPR24(7777-7786)
IEEE DOI Code:
WWW Link.
2410
Degradation, Image resolution, Image synthesis,
Ordinary differential equations, Diffusion models, Fast Sampling
BibRef
Lee, H.Y.[Hsin-Ying],
Tseng, H.Y.[Hung-Yu],
Lee, H.Y.[Hsin-Ying],
Yang, M.H.[Ming-Hsuan],
Exploiting Diffusion Prior for Generalizable Dense Prediction,
CVPR24(7861-7871)
IEEE DOI Code:
WWW Link.
2410
Adaptation models, Visualization, Training data,
Stochastic processes, Estimation, Diffusion processes,
image generation
BibRef
Koley, S.[Subhadeep],
Bhunia, A.K.[Ayan Kumar],
Sekhri, D.[Deeptanshu],
Sain, A.[Aneeshan],
Chowdhury, P.N.[Pinaki Nath],
Xiang, T.[Tao],
Song, Y.Z.[Yi-Zhe],
It's All About Your Sketch: Democratising Sketch Control in Diffusion
Models,
CVPR24(7204-7214)
IEEE DOI
2410
Adaptation models, Adaptive systems, Navigation, Generative AI,
Image retrieval, Process control, Streaming media
BibRef
Wang, Y.[Yibo],
Gao, R.Y.[Rui-Yuan],
Chen, K.[Kai],
Zhou, K.Q.[Kai-Qiang],
Cai, Y.J.[Ying-Jie],
Hong, L.Q.[Lan-Qing],
Li, Z.G.[Zhen-Guo],
Jiang, L.H.[Li-Hui],
Yeung, D.Y.[Dit-Yan],
Xu, Q.[Qiang],
Zhang, K.[Kai],
DetDiffusion: Synergizing Generative and Perceptive Models for
Enhanced Data Generation and Perception,
CVPR24(7246-7255)
IEEE DOI
2410
Image segmentation, Image recognition, Image synthesis,
Training data, Object detection, Diffusion models, Data augmentation
BibRef
Zhang, P.Z.[Peng-Ze],
Yin, H.[Hubery],
Li, C.[Chen],
Xie, X.H.[Xiao-Hua],
Tackling the Singularities at the Endpoints of Time Intervals in
Diffusion Models,
CVPR24(6945-6954)
IEEE DOI
2410
Training, Brightness, Gaussian distribution, Diffusion models,
Diffusion Model, Generative Model, Singularity
BibRef
Hong, S.[Seongmin],
Lee, K.[Kyeonghyun],
Jeon, S.Y.[Suh Yoon],
Bae, H.[Hyewon],
Chun, S.Y.[Se Young],
On Exact Inversion of DPM-Solvers,
CVPR24(7069-7078)
IEEE DOI
2410
Noise, Noise reduction, Watermarking, Diffusion models, Robustness,
Diffusion, Inversion, DPM-Solver
BibRef
Wang, H.J.[Hong-Jie],
Liu, D.[Difan],
Kang, Y.[Yan],
Li, Y.J.[Yi-Jun],
Lin, Z.[Zhe],
Jha, N.K.[Niraj K.],
Liu, Y.C.[Yu-Chen],
Attention-Driven Training-Free Efficiency Enhancement of Diffusion
Models,
CVPR24(16080-16089)
IEEE DOI Code:
WWW Link.
2410
Image quality, Schedules, Costs, Convolution, Computational modeling,
Noise reduction, diffusion model, training-free, efficiency,
attention map
BibRef
Kang, J.[Junoh],
Choi, J.[Jinyoung],
Choi, S.[Sungik],
Han, B.H.[Bo-Hyung],
Observation-Guided Diffusion Probabilistic Models,
CVPR24(8323-8331)
IEEE DOI Code:
WWW Link.
2410
Training, Accuracy, Computational modeling, Noise reduction,
Quality control, Diffusion models, Robustness, generative models,
diffusion models
BibRef
Chen, C.[Chen],
Liu, D.[Daochang],
Xu, C.[Chang],
Towards Memorization-Free Diffusion Models,
CVPR24(8425-8434)
IEEE DOI
2410
Image quality, Training, Measurement, Refining, Noise reduction,
Training data, Reliability theory, Diffusion Models, Memorization
BibRef
Qi, L.[Lu],
Yang, L.[Lehan],
Guo, W.D.[Wei-Dong],
Xu, Y.[Yu],
Du, B.[Bo],
Jampani, V.[Varun],
Yang, M.H.[Ming-Hsuan],
UniGS: Unified Representation for Image Generation and Segmentation,
CVPR24(6305-6315)
IEEE DOI
2410
Training, Image segmentation, Image synthesis,
Image color analysis, Pipelines, Training data, Transforms, diffusion
BibRef
Wang, L.Z.[Le-Zhong],
Frisvad, J.R.[Jeppe Revall],
Jensen, M.B.[Mark Bo],
Bigdeli, S.A.[Siavash Arjomand],
StereoDiffusion: Training-Free Stereo Image Generation Using Latent
Diffusion Models,
GCV24(7416-7425)
IEEE DOI
2410
Image quality, Image synthesis, Extended reality, Pipelines,
Noise reduction, Diffusion models, Deep Image/Video Synthesis,
Stable Diffusion
BibRef
Sharma, N.[Nakul],
Tripathi, A.[Aditay],
Chakraborty, A.[Anirban],
Mishra, A.[Anand],
Sketch-guided Image Inpainting with Partial Discrete Diffusion
Process,
NTIRE24(6024-6034)
IEEE DOI Code:
WWW Link.
2410
Visualization, Shape, Semantics, Diffusion processes, Text to image,
Transformers
BibRef
Guo, J.Y.[Jia-Yi],
Xu, X.Q.[Xing-Qian],
Pu, Y.F.[Yi-Fan],
Ni, Z.[Zanlin],
Wang, C.F.[Chao-Fei],
Vasu, M.[Manushree],
Song, S.[Shiji],
Huang, G.[Gao],
Shi, H.[Humphrey],
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models,
CVPR24(7548-7558)
IEEE DOI Code:
WWW Link.
2410
Training, Measurement, Interpolation, Visualization, Fluctuations,
Perturbation methods, Text to image
BibRef
Lyu, M.Y.[Meng-Yao],
Yang, Y.H.[Yu-Hong],
Hong, H.[Haiwen],
Chen, H.[Hui],
Jin, X.[Xuan],
He, Y.[Yuan],
Xue, H.[Hui],
Han, J.G.[Jun-Gong],
Ding, G.[Guiguang],
One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models
and Erasing Applications,
CVPR24(7559-7568)
IEEE DOI Code:
WWW Link.
2410
Deformable models, Adaptation models, Costs, Deformation,
Text to image, Diffusion models, Permeability, Diffusion Models, Concept Erasing
BibRef
Yang, L.[Ling],
Qian, H.T.[Hao-Tian],
Zhang, Z.L.[Zhi-Ling],
Liu, J.W.[Jing-Wei],
Cui, B.[Bin],
Structure-Guided Adversarial Training of Diffusion Models,
CVPR24(7256-7266)
IEEE DOI
2410
Training, Manifolds, Image synthesis, Noise reduction, Text to image,
Diffusion models, Data models, Diffusion models, generative models,
Image generation
BibRef
Xing, X.M.[Xi-Ming],
Zhou, H.T.[Hai-Tao],
Wang, C.[Chuang],
Zhang, J.[Jing],
Xu, D.[Dong],
Yu, Q.[Qian],
SVGDreamer: Text Guided SVG Generation with Diffusion Model,
CVPR24(4546-4555)
IEEE DOI Code:
WWW Link.
2410
Visualization, Image color analysis, Shape, Text to image, Process control,
Diffusion models, vector graphics, SVG, text-to-svg, Diffusion
BibRef
Parihar, R.[Rishubh],
Bhat, A.[Abhijnya],
Basu, A.[Abhipsa],
Mallick, S.[Saswat],
Kundu, J.N.[Jogendra Nath],
Babu, R.V.[R. Venkatesh],
Balancing Act: Distribution-Guided Debiasing in Diffusion Models,
CVPR24(6668-6678)
IEEE DOI
2410
Training, Image synthesis, Semantics, Noise reduction, Text to image,
Diffusion models, Data augmentation, Debiasing, diffusion models,
generative models
BibRef
Liu, C.[Chang],
Wu, H.N.[Hao-Ning],
Zhong, Y.J.[Yu-Jie],
Zhang, X.Y.[Xiao-Yun],
Wang, Y.F.[Yan-Feng],
Xie, W.[Weidi],
Intelligent Grimm: Open-ended Visual Storytelling via Latent
Diffusion Models,
CVPR24(6190-6200)
IEEE DOI Code:
WWW Link.
2410
Visualization, Electronic publishing, Computational modeling,
Pipelines, Text to image, Image sequences, Diffusion Models
BibRef
Wimbauer, F.[Felix],
Wu, B.[Bichen],
Schoenfeld, E.[Edgar],
Dai, X.L.[Xiao-Liang],
Hou, J.[Ji],
He, Z.J.[Zi-Jian],
Sanakoyeu, A.[Artsiom],
Zhang, P.Z.[Pei-Zhao],
Tsai, S.[Sam],
Kohler, J.[Jonas],
Rupprecht, C.[Christian],
Cremers, D.[Daniel],
Vajda, P.[Peter],
Wang, J.L.[Jia-Liang],
Cache Me if You Can: Accelerating Diffusion Models through Block
Caching,
CVPR24(6211-6220)
IEEE DOI
2410
Image quality, Visualization, Schedules, Image synthesis,
Computational modeling, Noise reduction, Noise, diffusion, fid
BibRef
Wang, Z.C.[Zhi-Cai],
Wei, L.H.[Long-Hui],
Wang, T.[Tan],
Chen, H.Y.[He-Yu],
Hao, Y.B.[Yan-Bin],
Wang, X.[Xiang],
He, X.N.[Xiang-Nan],
Tian, Q.[Qi],
Enhance Image Classification via Inter-Class Image Mixup with
Diffusion Model,
CVPR24(17223-17233)
IEEE DOI Code:
WWW Link.
2410
Training, Computational modeling, Text to image, Data augmentation,
Diffusion models, diffusion model, data augmentation
BibRef
Hsiao, Y.T.[Yi-Ting],
Khodadadeh, S.[Siavash],
Duarte, K.[Kevin],
Lin, W.A.[Wei-An],
Qu, H.[Hui],
Kwon, M.[Mingi],
Kalarot, R.[Ratheesh],
Plug-and-Play Diffusion Distillation,
CVPR24(13743-13752)
IEEE DOI
2410
Training, Visualization, Image synthesis, Computational modeling,
Text to image, Diffusion processes, distillation, model efficiency,
diffusion model
BibRef
Zhan, C.L.[Chen-Lu],
Lin, Y.[Yu],
Wang, G.A.[Gao-Ang],
Wang, H.W.[Hong-Wei],
Wu, J.[Jian],
MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided
Diffusion with Visual Invariant,
CVPR24(11502-11512)
IEEE DOI
2410
Visualization, Adaptation models, Technological innovation,
Magnetic resonance imaging, Text to image, Medical services,
Diffusion Model
BibRef
Kant, Y.[Yash],
Siarohin, A.[Aliaksandr],
Wu, Z.[Ziyi],
Vasilkovsky, M.[Michael],
Qian, G.C.[Guo-Cheng],
Ren, J.[Jian],
Guler, R.A.[Riza Alp],
Ghanem, B.[Bernard],
Tulyakov, S.[Sergey],
Gilitschenski, I.[Igor],
SPAD: Spatially Aware Multi-View Diffusers,
CVPR24(10026-10038)
IEEE DOI
2410
Geometry, Text to image, Transforms, Cameras, Diffusion models,
Encoding, novel view synthesis, diffusion
BibRef
Starodubcev, N.[Nikita],
Baranchuk, D.[Dmitry],
Fedorov, A.[Artem],
Babenko, A.[Artem],
Your Student is Better than Expected: Adaptive Teacher-Student
Collaboration for Text-Conditional Diffusion Models,
CVPR24(9275-9285)
IEEE DOI
2410
Adaptation models, Computational modeling, Pipelines,
Text to image, Collaboration, Diffusion models,
Image and video synthesis and generation
BibRef
Ran, L.M.[Ling-Min],
Cun, X.D.[Xiao-Dong],
Liu, J.W.[Jia-Wei],
Zhao, R.[Rui],
Zijie, S.[Song],
Wang, X.T.[Xin-Tao],
Keppo, J.[Jussi],
Shou, M.Z.[Mike Zheng],
X-Adapter: Universal Compatibility of Plugins for Upgraded Diffusion
Model,
CVPR24(8775-8784)
IEEE DOI Code:
WWW Link.
2410
Training, Connectors, Adaptation models, Noise reduction,
Text to image, Diffusion models, Data models
BibRef
Liu, Y.J.[Yu-Jian],
Zhang, Y.[Yang],
Jaakkola, T.[Tommi],
Chang, S.Y.[Shi-Yu],
Correcting Diffusion Generation Through Resampling,
CVPR24(8713-8723)
IEEE DOI Code:
WWW Link.
2410
Image quality, Image synthesis, Filtering, Computational modeling,
Text to image, Detectors, image generation, diffusion model, particle filtering
BibRef
Yan, J.N.[Jing Nathan],
Gu, J.[Jiatao],
Rush, A.M.[Alexander M.],
Diffusion Models Without Attention,
CVPR24(8239-8249)
IEEE DOI
2410
Training, Image resolution, Computational modeling,
Noise reduction, Text to image, Computer architecture
BibRef
Wang, J.Y.[Jun-Yan],
Sun, Z.H.[Zhen-Hong],
Tan, Z.Y.[Zhi-Yu],
Chen, X.B.[Xuan-Bai],
Chen, W.H.[Wei-Hua],
Li, H.[Hao],
Zhang, C.[Cheng],
Song, Y.[Yang],
Towards Effective Usage of Human-Centric Priors in Diffusion Models
for Text-based Human Image Generation,
CVPR24(8446-8455)
IEEE DOI Code:
WWW Link.
2410
Accuracy, Image synthesis, Semantics, Text to image,
Diffusion processes, Diffusion models
BibRef
Feng, Y.T.[Yu-Tong],
Gong, B.[Biao],
Chen, D.[Di],
Shen, Y.J.[Yu-Jun],
Liu, Y.[Yu],
Zhou, J.[Jingren],
Ranni: Taming Text-to-Image Diffusion for Accurate Instruction
Following,
CVPR24(4744-4753)
IEEE DOI
2410
Visualization, Protocols, Semantics, Pipelines, Text to image,
Diffusion models, Generators, diffusion model, text-to-image
BibRef
Lu, S.L.[Shi-Lin],
Wang, Z.[Zilan],
Li, L.[Leyang],
Liu, Y.Z.[Yan-Zhu],
Kong, A.W.K.[Adams Wai-Kin],
MACE: Mass Concept Erasure in Diffusion Models,
CVPR24(6430-6440)
IEEE DOI Code:
WWW Link.
2410
Codes, Text to image, Interference, Diffusion models,
Generative AI, AI security, diffusion model,
concept editing
BibRef
Nguyen, T.H.[Thuan Hoang],
Tran, A.[Anh],
SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational
Score Distillation,
CVPR24(7807-7816)
IEEE DOI
2410
Training, Solid modeling, Text to image, Diffusion models,
Neural radiance field, Data models
BibRef
Cao, C.J.[Chen-Jie],
Cai, Y.[Yunuo],
Dong, Q.[Qiaole],
Wang, Y.K.[Yi-Kai],
Fu, Y.W.[Yan-Wei],
LeftRefill: Filling Right Canvas based on Left Reference through
Generalized Text-to-Image Diffusion Model,
CVPR24(7705-7715)
IEEE DOI Code:
WWW Link.
2410
Adaptation models, Image synthesis, Text to image, Diffusion models,
Filling, Diffusion Model, Image Inpainting
BibRef
Mo, S.C.[Si-Cheng],
Mu, F.Z.[Fang-Zhou],
Lin, K.H.[Kuan Heng],
Liu, Y.L.[Yan-Li],
Guan, B.[Bochen],
Li, Y.[Yin],
Zhou, B.[Bolei],
FreeControl: Training-Free Spatial Control of Any Text-to-Image
Diffusion Model with Any Condition,
CVPR24(7465-7475)
IEEE DOI Code:
WWW Link.
2410
Visualization, Text to image,
Diffusion models, Feature extraction,
Controllable generation
BibRef
Mahajan, S.[Shweta],
Rahman, T.[Tanzila],
Yi, K.M.[Kwang Moo],
Sigal, L.[Leonid],
Prompting Hard or Hardly Prompting: Prompt Inversion for
Text-to-Image Diffusion Models,
CVPR24(6808-6817)
IEEE DOI
2410
Vocabulary, Visualization, Image synthesis, Semantics, Text to image,
Diffusion processes, Diffusion models
BibRef
Menon, S.[Sachit],
Misra, I.[Ishan],
Girdhar, R.[Rohit],
Generating Illustrated Instructions,
CVPR24(6274-6284)
IEEE DOI
2410
Measurement, Visualization, Large language models, Text to image,
Diffusion models, diffusion, multimodal,
text-to-image
BibRef
Yang, J.Y.[Jing-Yuan],
Feng, J.W.[Jia-Wei],
Huang, H.[Hui],
EmoGen: Emotional Image Content Generation with Text-to-Image
Diffusion Models,
CVPR24(6358-6368)
IEEE DOI Code:
WWW Link.
2410
Measurement, Visualization, Image color analysis, Image synthesis,
Semantics, Text to image
BibRef
Yang, Y.J.[Yi-Jun],
Gao, R.[Ruiyuan],
Wang, X.[Xiaosen],
Ho, T.Y.[Tsung-Yi],
Xu, N.[Nan],
xu, Q.[Qiang],
MMA-Diffusion: MultiModal Attack on Diffusion Models,
CVPR24(7737-7746)
IEEE DOI Code:
WWW Link.
2410
Visualization, Filters, Current measurement,
Computational modeling, Text to image, Diffusion models,
Adversarial attack
BibRef
Hedlin, E.[Eric],
Sharma, G.[Gopal],
Mahajan, S.[Shweta],
He, X.Z.[Xing-Zhe],
Isack, H.[Hossam],
Kar, A.[Abhishek],
Rhodin, H.[Helge],
Tagliasacchi, A.[Andrea],
Yi, K.M.[Kwang Moo],
Unsupervised Keypoints from Pretrained Diffusion Models,
CVPR24(22820-22830)
IEEE DOI
2410
Codes, Noise reduction, Neural networks, Text to image,
Diffusion models, Diffusion models,
emergent understandings
BibRef
Sato, T.[Takami],
Yue, J.[Justin],
Chen, N.[Nanze],
Wang, N.F.[Ning-Fei],
Chen, Q.A.[Qi Alfred],
Intriguing Properties of Diffusion Models: An Empirical Study of the
Natural Attack Capability in Text-to-Image Generative Models,
CVPR24(24635-24644)
IEEE DOI
2410
Noise reduction, Text to image, Artificial neural networks,
Visual systems, Predictive models, Diffusion models, Safety
BibRef
Smith, J.S.[James Seale],
Hsu, Y.C.[Yen-Chang],
Kira, Z.[Zsolt],
Shen, Y.L.[Yi-Lin],
Jin, H.X.[Hong-Xia],
Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters,
WhatNext24(1744-1754)
IEEE DOI
2410
Training, Costs, Text to image,
Benchmark testing, Diffusion models,
text-to-image customization
BibRef
Tudosiu, P.D.[Petru-Daniel],
Yang, Y.X.[Yong-Xin],
Zhang, S.F.[Shi-Feng],
Chen, F.[Fei],
McDonagh, S.[Steven],
Lampouras, G.[Gerasimos],
Iacobacci, I.[Ignacio],
Parisot, S.[Sarah],
MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image
Generation,
CVPR24(22413-22422)
IEEE DOI Code:
WWW Link.
2410
Training, Image segmentation, Annotations, Pipelines, Text to image,
Image decomposition, Software, Dataset, Text-to-Image Generation,
Diffusion Models
BibRef
Xu, X.Q.[Xing-Qian],
Guo, J.Y.[Jia-Yi],
Wang, Z.Y.[Zhang-Yang],
Huang, G.[Gao],
Essa, I.[Irfan],
Shi, H.[Humphrey],
Prompt-Free Diffusion: Taking 'Text' Out of Text-to-Image Diffusion
Models,
CVPR24(8682-8692)
IEEE DOI
2410
Visualization, Pain, Image synthesis, Computational modeling,
Semantics, Noise, Text to image, Generative Model, Image Editing, Text-to-Image
BibRef
Li, H.[Hang],
Shen, C.Z.[Cheng-Zhi],
Torr, P.[Philip],
Tresp, V.[Volker],
Gu, J.D.[Jin-Dong],
Self-Discovering Interpretable Diffusion Latent Directions for
Responsible Text-to-Image Generation,
CVPR24(12006-12016)
IEEE DOI Code:
WWW Link.
2410
Ethics, Prevention and mitigation, Semantics, Text to image,
Diffusion models, Vectors, Text-to-Image Generation,
Explainability and Transparency
BibRef
Li, H.[Hao],
Zou, Y.[Yang],
Wang, Y.[Ying],
Majumder, O.[Orchid],
Xie, Y.S.[Yu-Sheng],
Manmatha, R.,
Swaminathan, A.[Ashwin],
Tu, Z.W.[Zhuo-Wen],
Ermon, S.[Stefano],
Soatto, S.[Stefano],
On the Scalability of Diffusion-based Text-to-Image Generation,
CVPR24(9400-9409)
IEEE DOI
2410
Training, Costs, Systematics, Computational modeling, Scalability,
Noise reduction, Text to image, diffusion models, text-to-image,
Transformers
BibRef
Guo, X.[Xiefan],
Liu, J.L.[Jin-Lin],
Cui, M.M.[Miao-Miao],
Li, J.[Jiankai],
Yang, H.Y.[Hong-Yu],
Huang, D.[Di],
Initno: Boosting Text-to-Image Diffusion Models via Initial Noise
Optimization,
CVPR24(9380-9389)
IEEE DOI Code:
WWW Link.
2410
Navigation, Instruments, Noise, Pipelines, Text to image, Aerospace electronics
BibRef
Shen, D.[Dazhong],
Song, G.L.[Guang-Lu],
Xue, Z.[Zeyue],
Wang, F.Y.[Fu-Yun],
Liu, Y.[Yu],
Rethinking the Spatial Inconsistency in Classifier-Free Diffusion
Guidance,
CVPR24(9370-9379)
IEEE DOI Code:
WWW Link.
2410
Image quality, Training, Costs, Semantic segmentation, Semantics,
Noise reduction, Text-to-Image Diffusion Models,
Semantic Segmentation
BibRef
Zhou, Y.F.[Yu-Fan],
Zhang, R.[Ruiyi],
Gu, J.X.[Jiu-Xiang],
Sun, T.[Tong],
Customization Assistant for Text-to-image Generation,
CVPR24(9182-9191)
IEEE DOI
2410
Training, Large language models, Text to image, Diffusion models,
Testing
BibRef
Meral, T.H.S.[Tuna Han Salih],
Simsar, E.[Enis],
Tombari, F.[Federico],
Yanardag, P.[Pinar],
CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image
Diffusion Models,
CVPR24(9005-9014)
IEEE DOI
2410
Source coding, Computational modeling, Semantics, Text to image,
Benchmark testing, Diffusion models,
Semantic fidelity
BibRef
Jiang, Z.Z.[Zeyin-Zi],
Mao, C.J.[Chao-Jie],
Pan, Y.L.[Yu-Lin],
Han, Z.[Zhen],
Zhang, J.F.[Jing-Feng],
SCEdit: Efficient and Controllable Image Diffusion Generation via
Skip Connection Editing,
CVPR24(8995-9004)
IEEE DOI Code:
WWW Link.
2410
Training, Adaptation models, Tuners, Image synthesis, Text to image,
Diffusion models, Diffusion model, Text-to-image generation,
Efficient Tuning
BibRef
Kim, C.[Changhoon],
Min, K.[Kyle],
Patel, M.[Maitreya],
Cheng, S.[Sheng],
Yang, Y.Z.[Ye-Zhou],
WOUAF: Weight Modulation for User Attribution and Fingerprinting in
Text-to-Image Diffusion Models,
CVPR24(8974-8983)
IEEE DOI Code:
WWW Link.
2410
Solid modeling, Computational modeling,
Prevention and mitigation, Text to image, Modulation,
Generative Model
BibRef
Kwon, G.[Gihyun],
Jenni, S.[Simon],
Li, D.Z.[Ding-Zeyu],
Lee, J.Y.[Joon-Young],
Ye, J.C.[Jong Chul],
Heilbron, F.C.[Fabian Caba],
Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models,
CVPR24(8880-8889)
IEEE DOI
2410
Fuses, Semantics, Text to image, Diffusion models,
Optimization, Text-to-image Model,
Multi-concept
BibRef
Koley, S.[Subhadeep],
Bhunia, A.K.[Ayan Kumar],
Sain, A.[Aneeshan],
Chowdhury, P.N.[Pinaki Nath],
Xiang, T.[Tao],
Song, Y.Z.[Yi-Zhe],
Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers,
CVPR24(16826-16837)
IEEE DOI
2410
Visualization, Adaptation models, Shape, Pipelines, Image retrieval,
Text to image, Benchmark testing
BibRef
Zhao, L.[Lin],
Zhao, T.C.[Tian-Chen],
Lin, Z.[Zinan],
Ning, X.F.[Xue-Fei],
Dai, G.H.[Guo-Hao],
Yang, H.Z.[Hua-Zhong],
Wang, Y.[Yu],
FlashEval: Towards Fast and Accurate Evaluation of Text-to-Image
Diffusion Generative Models,
CVPR24(16122-16131)
IEEE DOI Code:
WWW Link.
2410
Training, Schedules, Quantization (signal), Computational modeling,
Text to image, Training data, Diffusion models
BibRef
Azarian, K.[Kambiz],
Das, D.[Debasmit],
Hou, Q.Q.[Qi-Qi],
Porikli, F.M.[Fatih M.],
Segmentation-Free Guidance for Text-to-Image Diffusion Models,
GCV24(7520-7529)
IEEE DOI
2410
Image segmentation, Costs, Image color analysis, Text to image,
Focusing, Switches
BibRef
Xu, Y.[Yanwu],
Zhao, Y.[Yang],
Xiao, Z.S.[Zhi-Sheng],
Hou, T.B.[Ting-Bo],
UFOGen: You Forward Once Large Scale Text-to-Image Generation via
Diffusion GANs,
CVPR24(8196-8206)
IEEE DOI
2410
Image synthesis, Computational modeling, Text to image, Propulsion,
Diffusion models, Hybrid power systems, diffusion models,
GANs
BibRef
Huang, R.H.[Run-Hui],
Han, J.H.[Jian-Hua],
Lu, G.S.[Guan-Song],
Liang, X.D.[Xiao-Dan],
Zeng, Y.H.[Yi-Han],
Zhang, W.[Wei],
Xu, H.[Hang],
DiffDis: Empowering Generative Diffusion Model with Cross-Modal
Discrimination Capability,
ICCV23(15667-15677)
IEEE DOI
2401
BibRef
Yang, X.Y.[Xing-Yi],
Wang, X.C.[Xin-Chao],
Diffusion Model as Representation Learner,
ICCV23(18892-18903)
IEEE DOI Code:
WWW Link.
2401
BibRef
Nair, N.G.[Nithin Gopalakrishnan],
Cherian, A.[Anoop],
Lohit, S.[Suhas],
Wang, Y.[Ye],
Koike-Akino, T.[Toshiaki],
Patel, V.M.[Vishal M.],
Marks, T.K.[Tim K.],
Steered Diffusion: A Generalized Framework for Plug-and-Play
Conditional Image Synthesis,
ICCV23(20793-20803)
IEEE DOI
2401
BibRef
Wang, Z.D.[Zhen-Dong],
Bao, J.M.[Jian-Min],
Zhou, W.G.[Wen-Gang],
Wang, W.[Weilun],
Hu, H.[Hezhen],
Chen, H.[Hong],
Li, H.Q.[Hou-Qiang],
DIRE for Diffusion-Generated Image Detection,
ICCV23(22388-22398)
IEEE DOI Code:
WWW Link.
2401
BibRef
Hong, S.[Susung],
Lee, G.[Gyuseong],
Jang, W.[Wooseok],
Kim, S.[Seungryong],
Improving Sample Quality of Diffusion Models Using Self-Attention
Guidance,
ICCV23(7428-7437)
IEEE DOI
2401
BibRef
Feng, B.T.[Berthy T.],
Smith, J.[Jamie],
Rubinstein, M.[Michael],
Chang, H.[Huiwen],
Bouman, K.L.[Katherine L.],
Freeman, W.T.[William T.],
Score-Based Diffusion Models as Principled Priors for Inverse Imaging,
ICCV23(10486-10497)
IEEE DOI
2401
BibRef
Zhang, L.[Lvmin],
Rao, A.[Anyi],
Agrawala, M.[Maneesh],
Adding Conditional Control to Text-to-Image Diffusion Models,
ICCV23(3813-3824)
IEEE DOI
2401
Award, Marr Price, ICCV.
BibRef
Zhao, W.L.[Wen-Liang],
Rao, Y.M.[Yong-Ming],
Liu, Z.[Zuyan],
Liu, B.[Benlin],
Zhou, J.[Jie],
Lu, J.W.[Ji-Wen],
Unleashing Text-to-Image Diffusion Models for Visual Perception,
ICCV23(5706-5716)
IEEE DOI Code:
WWW Link.
2401
BibRef
Wu, Q.C.[Qiu-Cheng],
Liu, Y.J.[Yu-Jian],
Zhao, H.[Handong],
Bui, T.[Trung],
Lin, Z.[Zhe],
Zhang, Y.[Yang],
Chang, S.Y.[Shi-Yu],
Harnessing the Spatial-Temporal Attention of Diffusion Models for
High-Fidelity Text-to-Image Synthesis,
ICCV23(7732-7742)
IEEE DOI
2401
BibRef
Zhao, J.[Jing],
Zheng, H.[Heliang],
Wang, C.[Chaoyue],
Lan, L.[Long],
Yang, W.J.[Wen-Jing],
MagicFusion: Boosting Text-to-Image Generation Performance by Fusing
Diffusion Models,
ICCV23(22535-22545)
IEEE DOI Code:
WWW Link.
2401
BibRef
Kumari, N.[Nupur],
Zhang, B.L.[Bing-Liang],
Wang, S.Y.[Sheng-Yu],
Shechtman, E.[Eli],
Zhang, R.[Richard],
Zhu, J.Y.[Jun-Yan],
Ablating Concepts in Text-to-Image Diffusion Models,
ICCV23(22634-22645)
IEEE DOI
2401
BibRef
Schwartz, I.[Idan],
Snæbjarnarson, V.[Vésteinn],
Chefer, H.[Hila],
Belongie, S.[Serge],
Wolf, L.[Lior],
Benaim, S.[Sagie],
Discriminative Class Tokens for Text-to-Image Diffusion Models,
ICCV23(22668-22678)
IEEE DOI Code:
WWW Link.
2401
BibRef
Patashnik, O.[Or],
Garibi, D.[Daniel],
Azuri, I.[Idan],
Averbuch-Elor, H.[Hadar],
Cohen-Or, D.[Daniel],
Localizing Object-level Shape Variations with Text-to-Image Diffusion
Models,
ICCV23(22994-23004)
IEEE DOI
2401
BibRef
Schramowski, P.[Patrick],
Brack, M.[Manuel],
Deiseroth, B.[Björn],
Kersting, K.[Kristian],
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in
Diffusion Models,
CVPR23(22522-22531)
IEEE DOI
2309
BibRef
Chen, C.[Chen],
Liu, D.[Daochang],
Ma, S.Q.[Si-Qi],
Nepal, S.[Surya],
Xu, C.[Chang],
Private Image Generation with Dual-Purpose Auxiliary Classifier,
CVPR23(20361-20370)
IEEE DOI
2309
BibRef
Zhang, Q.S.[Qin-Sheng],
Song, J.M.[Jia-Ming],
Huang, X.[Xun],
Chen, Y.X.[Yong-Xin],
Liu, M.Y.[Ming-Yu],
DiffCollage: Parallel Generation of Large Content with Diffusion
Models,
CVPR23(10188-10198)
IEEE DOI
2309
BibRef
Phung, H.[Hao],
Dao, Q.[Quan],
Tran, A.[Anh],
Wavelet Diffusion Models are fast and scalable Image Generators,
CVPR23(10199-10208)
IEEE DOI
2309
BibRef
Kim, S.W.[Seung Wook],
Brown, B.[Bradley],
Yin, K.X.[Kang-Xue],
Kreis, K.[Karsten],
Schwarz, K.[Katja],
Li, D.[Daiqing],
Rombach, R.[Robin],
Torralba, A.[Antonio],
Fidler, S.[Sanja],
NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion
Models,
CVPR23(8496-8506)
IEEE DOI
2309
BibRef
Zhu, Y.Z.[Yuan-Zhi],
Li, Z.H.[Zhao-Hai],
Wang, T.W.[Tian-Wei],
He, M.C.[Meng-Chao],
Yao, C.[Cong],
Conditional Text Image Generation with Diffusion Models,
CVPR23(14235-14244)
IEEE DOI
2309
BibRef
Zhou, Y.F.[Yu-Fan],
Liu, B.C.[Bing-Chen],
Zhu, Y.Z.[Yi-Zhe],
Yang, X.[Xiao],
Chen, C.Y.[Chang-You],
Xu, J.H.[Jin-Hui],
Shifted Diffusion for Text-to-image Generation,
CVPR23(10157-10166)
IEEE DOI
2309
BibRef
Li, M.H.[Mu-Heng],
Duan, Y.Q.[Yue-Qi],
Zhou, J.[Jie],
Lu, J.W.[Ji-Wen],
Diffusion-SDF: Text-to-Shape via Voxelized Diffusion,
CVPR23(12642-12651)
IEEE DOI
2309
BibRef
Wu, Q.C.[Qiu-Cheng],
Liu, Y.J.[Yu-Jian],
Zhao, H.[Handong],
Kale, A.[Ajinkya],
Bui, T.[Trung],
Yu, T.[Tong],
Lin, Z.[Zhe],
Zhang, Y.[Yang],
Chang, S.Y.[Shi-Yu],
Uncovering the Disentanglement Capability in Text-to-Image Diffusion
Models,
CVPR23(1900-1910)
IEEE DOI
2309
BibRef
Jain, A.[Ajay],
Xie, A.[Amber],
Abbeel, P.[Pieter],
VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models,
CVPR23(1911-1920)
IEEE DOI
2309
BibRef
Kumari, N.[Nupur],
Zhang, B.L.[Bing-Liang],
Zhang, R.[Richard],
Shechtman, E.[Eli],
Zhu, J.Y.[Jun-Yan],
Multi-Concept Customization of Text-to-Image Diffusion,
CVPR23(1931-1941)
IEEE DOI
2309
BibRef
Ruiz, N.[Nataniel],
Li, Y.Z.[Yuan-Zhen],
Jampani, V.[Varun],
Pritch, Y.[Yael],
Rubinstein, M.[Michael],
Aberman, K.[Kfir],
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for
Subject-Driven Generation,
CVPR23(22500-22510)
IEEE DOI
2309
BibRef
Liu, X.H.[Xi-Hui],
Park, D.H.[Dong Huk],
Azadi, S.[Samaneh],
Zhang, G.[Gong],
Chopikyan, A.[Arman],
Hu, Y.X.[Yu-Xiao],
Shi, H.[Humphrey],
Rohrbach, A.[Anna],
Darrell, T.J.[Trevor J.],
More Control for Free! Image Synthesis with Semantic Diffusion
Guidance,
WACV23(289-299)
IEEE DOI
2302
Image synthesis, Annotations, Image matching, Semantics,
Noise reduction, Probabilistic logic,
Vision + language and/or other modalities
BibRef
Pan, Z.H.[Zhi-Hong],
Zhou, X.[Xin],
Tian, H.[Hao],
Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image
Generation,
WACV23(4450-4460)
IEEE DOI
2302
Graphics, Training, Technological innovation, Adaptation models,
Adaptive systems, Art, Navigation,
Vision + language and/or other modalities
BibRef
Gu, S.Y.[Shu-Yang],
Chen, D.[Dong],
Bao, J.M.[Jian-Min],
Wen, F.[Fang],
Zhang, B.[Bo],
Chen, D.D.[Dong-Dong],
Yuan, L.[Lu],
Guo, B.N.[Bai-Ning],
Vector Quantized Diffusion Model for Text-to-Image Synthesis,
CVPR22(10686-10696)
IEEE DOI
2210
Image quality, Image resolution, Image synthesis,
Computational modeling, Noise reduction,
Vision+language
BibRef
Jing, B.[Bowen],
Corso, G.[Gabriele],
Berlinghieri, R.[Renato],
Jaakkola, T.[Tommi],
Subspace Diffusion Generative Models,
ECCV22(XXIII:274-289).
Springer DOI
2211
BibRef
Han, L.G.[Li-Gong],
Li, Y.X.[Yin-Xiao],
Zhang, H.[Han],
Milanfar, P.[Peyman],
Metaxas, D.N.[Dimitris N.],
Yang, F.[Feng],
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning,
ICCV23(7289-7300)
IEEE DOI
2401
BibRef
Nair, N.G.[Nithin Gopalakrishnan],
Bandara, W.G.C.[Wele Gedara Chaminda],
Patel, V.M.[Vishal M.],
Unite and Conquer: Plug and Play Multi-Modal Synthesis Using
Diffusion Models,
CVPR23(6070-6079)
IEEE DOI
2309
BibRef
Zheng, G.[Guangcong],
Li, S.M.[Sheng-Ming],
Wang, H.[Hui],
Yao, T.P.[Tai-Ping],
Chen, Y.[Yang],
Ding, S.H.[Shou-Hong],
Li, X.[Xi],
Entropy-Driven Sampling and Training Scheme for Conditional Diffusion
Generation,
ECCV22(XXII:754-769).
Springer DOI
2211
BibRef
Chapter on 3-D Object Description and Computation Techniques, Surfaces, Deformable, View Generation, Video Conferencing continues in
Learning Diffusion Models for Description or Text to Image Generation .