@inproceedings{bb102700,
AUTHOR = "Wimbauer, F. and Wu, B. and Schoenfeld, E. and Dai, X.L. and Hou, J. and He, Z.J. and Sanakoyeu, A. and Zhang, P.Z. and Tsai, S. and Kohler, J. and Rupprecht, C. and Cremers, D. and Vajda, P. and Wang, J.L.",
TITLE = "Cache Me if You Can: Accelerating Diffusion Models through Block
Caching",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6211-6220",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99416"}
@inproceedings{bb102701,
AUTHOR = "Dalva, Y. and Yanardag, P.",
TITLE = "NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery
of Interpretable Directions in Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24209-24218",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99417"}
@inproceedings{bb102702,
AUTHOR = "Wang, Z.C. and Wei, L.H. and Wang, T. and Chen, H.Y. and Hao, Y.B. and Wang, X. and He, X.N. and Tian, Q.",
TITLE = "Enhance Image Classification via Inter-Class Image Mixup with
Diffusion Model",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "17223-17233",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99418"}
@inproceedings{bb102703,
AUTHOR = "Hsiao, Y.T. and Khodadadeh, S. and Duarte, K. and Lin, W.A. and Qu, H. and Kwon, M. and Kalarot, R.",
TITLE = "Plug-and-Play Diffusion Distillation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13743-13752",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99419"}
@inproceedings{bb102704,
AUTHOR = "Zhan, C.L. and Lin, Y. and Wang, G.A. and Wang, H.W. and Wu, J.",
TITLE = "MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided
Diffusion with Visual Invariant",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11502-11512",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99420"}
@inproceedings{bb102705,
AUTHOR = "Kant, Y. and Siarohin, A. and Wu, Z. and Vasilkovsky, M. and Qian, G.C. and Ren, J. and Guler, R.A. and Ghanem, B. and Tulyakov, S. and Gilitschenski, I.",
TITLE = "SPAD: Spatially Aware Multi-View Diffusers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10026-10038",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99421"}
@inproceedings{bb102706,
AUTHOR = "Starodubcev, N. and Baranchuk, D. and Fedorov, A. and Babenko, A.",
TITLE = "Your Student is Better than Expected: Adaptive Teacher-Student
Collaboration for Text-Conditional Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9275-9285",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99422"}
@inproceedings{bb102707,
AUTHOR = "Ran, L.M. and Cun, X.D. and Liu, J.W. and Zhao, R. and Zijie, S. and Wang, X.T. and Keppo, J. and Shou, M.Z.",
TITLE = "X-Adapter: Universal Compatibility of Plugins for Upgraded Diffusion
Model",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8775-8784",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99423"}
@inproceedings{bb102708,
AUTHOR = "Liu, Y.J. and Zhang, Y. and Jaakkola, T. and Chang, S.Y.",
TITLE = "Correcting Diffusion Generation Through Resampling",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8713-8723",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99424"}
@inproceedings{bb102709,
AUTHOR = "Luo, G. and Darrell, T.J. and Wang, O. and Goldman, D.B. and Holynski, A.",
TITLE = "Readout Guidance: Learning Control from Diffusion Features",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8217-8227",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99425"}
@inproceedings{bb102710,
AUTHOR = "Wallace, B. and Dang, M. and Rafailov, R. and Zhou, L.Q. and Lou, A. and Purushwalkam, S. and Ermon, S. and Xiong, C.M. and Joty, S. and Naik, N.",
TITLE = "Diffusion Model Alignment Using Direct Preference Optimization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8228-8238",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99426"}
@inproceedings{bb102711,
AUTHOR = "Yan, J.N. and Gu, J. and Rush, A.M.",
TITLE = "Diffusion Models Without Attention",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8239-8249",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99427"}
@inproceedings{bb102712,
AUTHOR = "Gokaslan, A. and Cooper, A.F. and Collins, J. and Seguin, L. and Jacobson, A. and Patel, M. and Frankle, J. and Stephenson, C. and Kuleshov, V.",
TITLE = "Common Canvas: Open Diffusion Models Trained on Creative-Commons Images",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8250-8260",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99428"}
@inproceedings{bb102713,
AUTHOR = "Wang, J.Y. and Sun, Z.H. and Tan, Z.Y. and Chen, X.B. and Chen, W.H. and Li, H. and Zhang, C. and Song, Y.",
TITLE = "Towards Effective Usage of Human-Centric Priors in Diffusion Models
for Text-based Human Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8446-8455",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99429"}
@inproceedings{bb102714,
AUTHOR = "Feng, Y.T. and Gong, B. and Chen, D. and Shen, Y.J. and Liu, Y. and Zhou, J.",
TITLE = "Ranni: Taming Text-to-Image Diffusion for Accurate Instruction
Following",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "4744-4753",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99430"}
@inproceedings{bb102715,
AUTHOR = "Lu, S.L. and Wang, Z. and Li, L. and Liu, Y.Z. and Kong, A.W.K.",
TITLE = "MACE: Mass Concept Erasure in Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6430-6440",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99431"}
@inproceedings{bb102716,
AUTHOR = "Nam, J. and Kim, H. and Lee, D. and Jin, S. and Kim, S. and Chang, S.",
TITLE = "DreamMatcher: Appearance Matching Self-Attention for
Semantically-Consistent Text-to-Image Personalization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8100-8110",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99432"}
@inproceedings{bb102717,
AUTHOR = "Ham, C. and Fisher, M. and Hays, J. and Kolkin, N. and Liu, Y.C. and Zhang, R. and Hinz, T.",
TITLE = "Personalized Residuals for Concept-Driven Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8186-8195",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99433"}
@inproceedings{bb102718,
AUTHOR = "Nguyen, T.H. and Tran, A.",
TITLE = "SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational
Score Distillation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7807-7816",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99434"}
@inproceedings{bb102719,
AUTHOR = "Cao, C.J. and Cai, Y. and Dong, Q. and Wang, Y.K. and Fu, Y.W.",
TITLE = "LeftRefill: Filling Right Canvas based on Left Reference through
Generalized Text-to-Image Diffusion Model",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7705-7715",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99435"}
@inproceedings{bb102720,
AUTHOR = "Mo, S.C. and Mu, F.Z. and Lin, K.H. and Liu, Y.L. and Guan, B. and Li, Y. and Zhou, B.",
TITLE = "FreeControl: Training-Free Spatial Control of Any Text-to-Image
Diffusion Model with Any Condition",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7465-7475",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99436"}
@inproceedings{bb102721,
AUTHOR = "Mahajan, S. and Rahman, T. and Yi, K.M. and Sigal, L.",
TITLE = "Prompting Hard or Hardly Prompting: Prompt Inversion for
Text-to-Image Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6808-6817",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99437"}
@inproceedings{bb102722,
AUTHOR = "Zeng, Y. and Patel, V.M. and Wang, H.C. and Huang, X. and Wang, T.C. and Liu, M.Y. and Balaji, Y.",
TITLE = "JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized
Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6786-6795",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99438"}
@inproceedings{bb102723,
AUTHOR = "Menon, S. and Misra, I. and Girdhar, R.",
TITLE = "Generating Illustrated Instructions",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6274-6284",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99439"}
@inproceedings{bb102724,
AUTHOR = "Yang, J.Y. and Feng, J.W. and Huang, H.",
TITLE = "EmoGen: Emotional Image Content Generation with Text-to-Image
Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6358-6368",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99440"}
@inproceedings{bb102725,
AUTHOR = "Yang, Y.J. and Gao, R. and Wang, X. and Ho, T.Y. and Xu, N. and xu, Q.",
TITLE = "MMA-Diffusion: MultiModal Attack on Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7737-7746",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99441"}
@inproceedings{bb102726,
AUTHOR = "Hedlin, E. and Sharma, G. and Mahajan, S. and He, X.Z. and Isack, H. and Kar, A. and Rhodin, H. and Tagliasacchi, A. and Yi, K.M.",
TITLE = "Unsupervised Keypoints from Pretrained Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22820-22830",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99442"}
@inproceedings{bb102727,
AUTHOR = "Sato, T. and Yue, J. and Chen, N. and Wang, N.F. and Chen, Q.A.",
TITLE = "Intriguing Properties of Diffusion Models: An Empirical Study of the
Natural Attack Capability in Text-to-Image Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24635-24644",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99443"}
@inproceedings{bb102728,
AUTHOR = "Mo, W. and Zhang, T.Y. and Bai, Y. and Su, B. and Wen, J.R. and Yang, Q.",
TITLE = "Dynamic Prompt Optimizing for Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26617-26626",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99444"}
@inproceedings{bb102729,
AUTHOR = "Smith, J.S. and Hsu, Y.C. and Kira, Z. and Shen, Y.L. and Jin, H.X.",
TITLE = "Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters",
BOOKTITLE = WhatNext24,
YEAR = "2024",
PAGES = "1744-1754",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99445"}
@inproceedings{bb102730,
AUTHOR = "Zhang, G. and Wang, K. and Xu, X.Q. and Wang, Z.Y. and Shi, H.",
TITLE = "Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models",
BOOKTITLE = WhatNext24,
YEAR = "2024",
PAGES = "1755-1764",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99446"}
@inproceedings{bb102731,
AUTHOR = "Tudosiu, P.D. and Yang, Y.X. and Zhang, S.F. and Chen, F. and McDonagh, S. and Lampouras, G. and Iacobacci, I. and Parisot, S.",
TITLE = "MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22413-22422",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99447"}
@inproceedings{bb102732,
AUTHOR = "Pang, L.Y. and Yin, J. and Xie, H.R. and Wang, Q. and Li, Q. and Mao, X.D.",
TITLE = "Cross Initialization for Face Personalization of Text-to-Image Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8393-8403",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99448"}
@inproceedings{bb102733,
AUTHOR = "Xu, X.Q. and Guo, J.Y. and Wang, Z.Y. and Huang, G. and Essa, I. and Shi, H.",
TITLE = "Prompt-Free Diffusion: Taking 'Text' Out of Text-to-Image Diffusion
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8682-8692",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99449"}
@inproceedings{bb102734,
AUTHOR = "Qi, T.H. and Fang, S.C. and Wu, Y.Z. and Xie, H.T. and Liu, J.W. and Chen, L. and He, Q. and Zhang, Y.D.",
TITLE = "DEADiff: An Efficient Stylization Diffusion Model with Disentangled
Representations",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8693-8702",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99450"}
@inproceedings{bb102735,
AUTHOR = "Li, H. and Shen, C.Z. and Torr, P. and Tresp, V. and Gu, J.D.",
TITLE = "Self-Discovering Interpretable Diffusion Latent Directions for
Responsible Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12006-12016",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99451"}
@inproceedings{bb102736,
AUTHOR = "Li, H. and Zou, Y. and Wang, Y. and Majumder, O. and Xie, Y.S. and Manmatha, R. and Swaminathan, A. and Tu, Z.W. and Ermon, S. and Soatto, S.",
TITLE = "On the Scalability of Diffusion-based Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9400-9409",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99452"}
@inproceedings{bb102737,
AUTHOR = "Guo, X. and Liu, J.L. and Cui, M.M. and Li, J. and Yang, H.Y. and Huang, D.",
TITLE = "Initno: Boosting Text-to-Image Diffusion Models via Initial Noise
Optimization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9380-9389",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99453"}
@inproceedings{bb102738,
AUTHOR = "Shen, D. and Song, G.L. and Xue, Z. and Wang, F.Y. and Liu, Y.",
TITLE = "Rethinking the Spatial Inconsistency in Classifier-Free Diffusion
Guidance",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9370-9379",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99454"}
@inproceedings{bb102739,
AUTHOR = "Zhou, Y.F. and Zhang, R. and Gu, J.X. and Sun, T.",
TITLE = "Customization Assistant for Text-to-image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9182-9191",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99455"}
@inproceedings{bb102740,
AUTHOR = "Patel, M. and Kim, C. and Cheng, S. and Baral, C. and Yang, Y.Z.",
TITLE = "ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image
Generations",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9069-9078",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99456"}
@inproceedings{bb102741,
AUTHOR = "Meral, T.H.S. and Simsar, E. and Tombari, F. and Yanardag, P.",
TITLE = "CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image
Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9005-9014",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99457"}
@inproceedings{bb102742,
AUTHOR = "Jiang, Z.Z. and Mao, C.J. and Pan, Y.L. and Han, Z. and Zhang, J.F.",
TITLE = "SCEdit: Efficient and Controllable Image Diffusion Generation via
Skip Connection Editing",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8995-9004",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99458"}
@inproceedings{bb102743,
AUTHOR = "Kim, C. and Min, K. and Patel, M. and Cheng, S. and Yang, Y.Z.",
TITLE = "WOUAF: Weight Modulation for User Attribution and Fingerprinting in
Text-to-Image Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8974-8983",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99459"}
@inproceedings{bb102744,
AUTHOR = "Kwon, G. and Jenni, S. and Li, D.Z. and Lee, J.Y. and Ye, J.C. and Heilbron, F.C.",
TITLE = "Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8880-8889",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99460"}
@inproceedings{bb102745,
AUTHOR = "Kim, J. and Park, J. and Rhee, W.",
TITLE = "Selectively Informative Description can Reduce Undesired Embedding
Entanglements in Text-to-Image Personalization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8312-8322",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99461"}
@inproceedings{bb102746,
AUTHOR = "Koley, S. and Bhunia, A.K. and Sain, A. and Chowdhury, P.N. and Xiang, T. and Song, Y.Z.",
TITLE = "Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16826-16837",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99462"}
@inproceedings{bb102747,
AUTHOR = "Zhao, L. and Zhao, T.C. and Lin, Z. and Ning, X.F. and Dai, G.H. and Yang, H.Z. and Wang, Y.",
TITLE = "FlashEval: Towards Fast and Accurate Evaluation of Text-to-Image
Diffusion Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16122-16131",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99463"}
@inproceedings{bb102748,
AUTHOR = "Liu, H. and Sun, Z.C. and Mu, Y.D.",
TITLE = "Countering Personalized Text-to-Image Generation with Influence
Watermarks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12257-12267",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99464"}
@inproceedings{bb102749,
AUTHOR = "Azarian, K. and Das, D. and Hou, Q.Q. and Porikli, F.M.",
TITLE = "Segmentation-Free Guidance for Text-to-Image Diffusion Models",
BOOKTITLE = GCV24,
YEAR = "2024",
PAGES = "7520-7529",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99465"}
@inproceedings{bb102750,
AUTHOR = "Li, C. and Qi, Y. and Zeng, Q. and Lu, L.",
TITLE = "Comparison of Image Generation methods based on Diffusion Models",
BOOKTITLE = CVIDL23,
YEAR = "2023",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99466"}
@inproceedings{bb102751,
AUTHOR = "Xu, Y. and Zhao, Y. and Xiao, Z.S. and Hou, T.B.",
TITLE = "UFOGen: You Forward Once Large Scale Text-to-Image Generation via
Diffusion GANs",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8196-8206",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99467"}
@inproceedings{bb102752,
AUTHOR = "Huang, R.H. and Han, J.H. and Lu, G.S. and Liang, X.D. and Zeng, Y.H. and Zhang, W. and Xu, H.",
TITLE = "DiffDis: Empowering Generative Diffusion Model with Cross-Modal
Discrimination Capability",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15667-15677",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99468"}
@inproceedings{bb102753,
AUTHOR = "Yang, X.Y. and Wang, X.C.",
TITLE = "Diffusion Model as Representation Learner",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "18892-18903",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99469"}
@inproceedings{bb102754,
AUTHOR = "Nair, N.G. and Cherian, A. and Lohit, S. and Wang, Y. and Koike Akino, T. and Patel, V.M. and Marks, T.K.",
TITLE = "Steered Diffusion: A Generalized Framework for Plug-and-Play
Conditional Image Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20793-20803",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99470"}
@inproceedings{bb102755,
AUTHOR = "Wang, Z.D. and Bao, J.M. and Zhou, W.G. and Wang, W. and Hu, H. and Chen, H. and Li, H.Q.",
TITLE = "DIRE for Diffusion-Generated Image Detection",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22388-22398",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99471"}
@inproceedings{bb102756,
AUTHOR = "Hong, S. and Lee, G. and Jang, W. and Kim, S.",
TITLE = "Improving Sample Quality of Diffusion Models Using Self-Attention
Guidance",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7428-7437",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99472"}
@inproceedings{bb102757,
AUTHOR = "Feng, B.T. and Smith, J. and Rubinstein, M. and Chang, H. and Bouman, K.L. and Freeman, W.T.",
TITLE = "Score-Based Diffusion Models as Principled Priors for Inverse Imaging",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10486-10497",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99473"}
@inproceedings{bb102758,
AUTHOR = "Zhang, L. and Rao, A. and Agrawala, M.",
TITLE = "Adding Conditional Control to Text-to-Image Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3813-3824",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99474"}
@inproceedings{bb102759,
AUTHOR = "Zhao, W.L. and Rao, Y.M. and Liu, Z. and Liu, B. and Zhou, J. and Lu, J.W.",
TITLE = "Unleashing Text-to-Image Diffusion Models for Visual Perception",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5706-5716",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99475"}
@inproceedings{bb102760,
AUTHOR = "Wu, Q.C. and Liu, Y.J. and Zhao, H. and Bui, T. and Lin, Z. and Zhang, Y. and Chang, S.Y.",
TITLE = "Harnessing the Spatial-Temporal Attention of Diffusion Models for
High-Fidelity Text-to-Image Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7732-7742",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99476"}
@inproceedings{bb102761,
AUTHOR = "Zhao, J. and Zheng, H. and Wang, C. and Lan, L. and Yang, W.J.",
TITLE = "MagicFusion: Boosting Text-to-Image Generation Performance by Fusing
Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22535-22545",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99477"}
@inproceedings{bb102762,
AUTHOR = "Kumari, N. and Zhang, B.L. and Wang, S.Y. and Shechtman, E. and Zhang, R. and Zhu, J.Y.",
TITLE = "Ablating Concepts in Text-to-Image Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22634-22645",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99478"}
@inproceedings{bb102763,
AUTHOR = "Schwartz, I. and Snæbjarnarson, V. and Chefer, H. and Belongie, S. and Wolf, L. and Benaim, S.",
TITLE = "Discriminative Class Tokens for Text-to-Image Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22668-22678",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99479"}
@inproceedings{bb102764,
AUTHOR = "Patashnik, O. and Garibi, D. and Azuri, I. and Averbuch Elor, H. and Cohen Or, D.",
TITLE = "Localizing Object-level Shape Variations with Text-to-Image Diffusion
Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22994-23004",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99480"}
@inproceedings{bb102765,
AUTHOR = "Schramowski, P. and Brack, M. and Deiseroth, B. and Kersting, K.",
TITLE = "Safe Latent Diffusion: Mitigating Inappropriate Degeneration in
Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22522-22531",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99481"}
@inproceedings{bb102766,
AUTHOR = "Chen, C. and Liu, D. and Ma, S.Q. and Nepal, S. and Xu, C.",
TITLE = "Private Image Generation with Dual-Purpose Auxiliary Classifier",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20361-20370",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99482"}
@inproceedings{bb102767,
AUTHOR = "Zhang, Q.S. and Song, J.M. and Huang, X. and Chen, Y.X. and Liu, M.Y.",
TITLE = "DiffCollage: Parallel Generation of Large Content with Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10188-10198",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99483"}
@inproceedings{bb102768,
AUTHOR = "Phung, H. and Dao, Q. and Tran, A.",
TITLE = "Wavelet Diffusion Models are fast and scalable Image Generators",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10199-10208",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99484"}
@inproceedings{bb102769,
AUTHOR = "Kim, S.W. and Brown, B. and Yin, K.X. and Kreis, K. and Schwarz, K. and Li, D. and Rombach, R. and Torralba, A. and Fidler, S.",
TITLE = "NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "8496-8506",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99485"}
@inproceedings{bb102770,
AUTHOR = "Zhu, Y.Z. and Li, Z.H. and Wang, T.W. and He, M.C. and Yao, C.",
TITLE = "Conditional Text Image Generation with Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14235-14244",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99486"}
@inproceedings{bb102771,
AUTHOR = "Zhou, Y.F. and Liu, B.C. and Zhu, Y.Z. and Yang, X. and Chen, C.Y. and Xu, J.H.",
TITLE = "Shifted Diffusion for Text-to-image Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10157-10166",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99487"}
@inproceedings{bb102772,
AUTHOR = "Li, M.H. and Duan, Y.Q. and Zhou, J. and Lu, J.W.",
TITLE = "Diffusion-SDF: Text-to-Shape via Voxelized Diffusion",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "12642-12651",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99488"}
@inproceedings{bb102773,
AUTHOR = "Wu, Q.C. and Liu, Y.J. and Zhao, H. and Kale, A. and Bui, T. and Yu, T. and Lin, Z. and Zhang, Y. and Chang, S.Y.",
TITLE = "Uncovering the Disentanglement Capability in Text-to-Image Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1900-1910",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99489"}
@inproceedings{bb102774,
AUTHOR = "Jain, A. and Xie, A. and Abbeel, P.",
TITLE = "VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1911-1920",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99490"}
@inproceedings{bb102775,
AUTHOR = "Kumari, N. and Zhang, B.L. and Zhang, R. and Shechtman, E. and Zhu, J.Y.",
TITLE = "Multi-Concept Customization of Text-to-Image Diffusion",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1931-1941",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99491"}
@inproceedings{bb102776,
AUTHOR = "Ruiz, N. and Li, Y.Z. and Jampani, V. and Pritch, Y. and Rubinstein, M. and Aberman, K.",
TITLE = "DreamBooth: Fine Tuning Text-to-Image Diffusion Models for
Subject-Driven Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22500-22510",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99492"}
@inproceedings{bb102777,
AUTHOR = "Liu, X.H. and Park, D.H. and Azadi, S. and Zhang, G. and Chopikyan, A. and Hu, Y.X. and Shi, H. and Rohrbach, A. and Darrell, T.J.",
TITLE = "More Control for Free! Image Synthesis with Semantic Diffusion
Guidance",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "289-299",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99493"}
@inproceedings{bb102778,
AUTHOR = "Pan, Z.H. and Zhou, X. and Tian, H.",
TITLE = "Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image
Generation",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "4450-4460",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99494"}
@inproceedings{bb102779,
AUTHOR = "Gu, S.Y. and Chen, D. and Bao, J.M. and Wen, F. and Zhang, B. and Chen, D.D. and Yuan, L. and Guo, B.N.",
TITLE = "Vector Quantized Diffusion Model for Text-to-Image Synthesis",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10686-10696",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99495"}
@inproceedings{bb102780,
AUTHOR = "Jing, B. and Corso, G. and Berlinghieri, R. and Jaakkola, T.",
TITLE = "Subspace Diffusion Generative Models",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIII:274-289",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99496"}
@inproceedings{bb102781,
AUTHOR = "Han, L.G. and Li, Y.X. and Zhang, H. and Milanfar, P. and Metaxas, D.N. and Yang, F.",
TITLE = "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7289-7300",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99497"}
@inproceedings{bb102782,
AUTHOR = "Nair, N.G. and Bandara, W.G.C. and Patel, V.M.",
TITLE = "Unite and Conquer: Plug and Play Multi-Modal Synthesis Using
Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6070-6079",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99498"}
@inproceedings{bb102783,
AUTHOR = "Zheng, G. and Li, S.M. and Wang, H. and Yao, T.P. and Chen, Y. and Ding, S.H. and Li, X.",
TITLE = "Entropy-Driven Sampling and Training Scheme for Conditional Diffusion
Generation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXII:754-769",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99499"}
@inproceedings{bb102784,
AUTHOR = "Sehwag, V. and Hazirbas, C. and Gordo, A. and Ozgenel, F. and Ferrer, C.C.",
TITLE = "Generating High Fidelity Data from Low-density Regions using
Diffusion Models",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "11482-11491",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT99500"}
@article{bb102785,
AUTHOR = "Zhou, D. and Li, Y. and Ma, F. and Yang, Z.X. and Yang, Y.",
TITLE = "MIGC++: Advanced Multi-Instance Generation Controller for Image
Synthesis",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "3",
MONTH = "March",
PAGES = "1714-1728",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99501"}
@inproceedings{bb102786,
AUTHOR = "Zhou, D. and Li, Y. and Ma, F. and Zhang, X.T. and Yang, Y.",
TITLE = "MIGC: Multi-Instance Generation Controller for Text-to-Image
Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6818-6828",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99502"}
@article{bb102787,
AUTHOR = "Taghipour, A. and Ghahremani, M. and Bennamoun, M. and Rekavandi, A.M. and Laga, H. and Boussaid, F.",
TITLE = "Box It to Bind It: Unified Layout Control and Attribute Binding in
Text-to-Image Diffusion Models",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "8393-8407",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99503"}
@article{bb102788,
AUTHOR = "Zhu, J.Y. and Ma, H.M. and Chen, J.S. and Yuan, J.",
TITLE = "Object Detection Data Synthesis via Box-to-Image Generation Based on
Diffusion Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "557-571",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99504"}
@inproceedings{bb102789,
AUTHOR = "Wang, Z.X. and Peng, D. and Chen, F. and Yang, Y.W. and Lei, Y.J.",
TITLE = "Training-free Dense-Aligned Diffusion Guidance for Modular
Conditional Image Synthesis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13135-13145",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99505"}
@inproceedings{bb102790,
AUTHOR = "Duan, L. and Zhao, S.S. and Yan, W.J. and Li, Y. and Chen, Q.G. and Xu, Z. and Luo, W.H. and Zhang, K. and Gong, M.M. and Xia, G.S.",
TITLE = "UNIC-Adapter: Unified Image-Instruction Adapter with Multi-Modal
Transformer for Image Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7963-7973",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99506"}
@inproceedings{bb102791,
AUTHOR = "Patel, Z. and Serkh, K.",
TITLE = "Enhancing Image Layout Control with Loss-Guided Diffusion Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "3916-3924",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99507"}
@inproceedings{bb102792,
AUTHOR = "Arrabi, A. and Zhang, X.H. and Sultani, W. and Chen, C. and Wshah, S.",
TITLE = "Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and
Text Guidance",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5356-5366",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99508"}
@inproceedings{bb102793,
AUTHOR = "Guo, D.F. and Agarwal, S. and Lin, Y.H. and Kao, J.Y. and Chung, T. and Peng, N. and Bansal, M.",
TITLE = "Improving Faithfulness of Text-to-Image Diffusion Models through
Inference Intervention",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4077-4086",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99509"}
@inproceedings{bb102794,
AUTHOR = "Wang, Y.L. and Chen, Z.Y. and Zhong, L.J. and Ding, Z. and Tu, Z.W.",
TITLE = "Dolfin: Diffusion Layout Transformers Without Autoencoder",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LI: 326-343",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99510"}
@inproceedings{bb102795,
AUTHOR = "Iwai, S. and Osanai, A. and Kitada, S. and Omachi, S.",
TITLE = "Layout-corrector: Alleviating Layout Sticking Phenomenon in Discrete
Diffusion Model",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXIV: 92-110",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99511"}
@inproceedings{bb102796,
AUTHOR = "Shabani, M.A. and Wang, Z.W. and Liu, D. and Zhao, N.X. and Yang, J. and Furukawa, Y.",
TITLE = "Visual Layout Composer: Image-Vector Dual Diffusion Model for Design
Layout Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9222-9231",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99512"}
@inproceedings{bb102797,
AUTHOR = "Ren, J.W. and Xu, M.M. and Wu, J.C. and Liu, Z.W. and Xiang, T. and Toisoul, A.",
TITLE = "Move Anything with Layered Scene Diffusion",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6380-6389",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99513"}
@inproceedings{bb102798,
AUTHOR = "Habibian, A. and Ghodrati, A. and Fathima, N. and Sautiere, G. and Garrepalli, R. and Porikli, F.M. and Petersen, J.",
TITLE = "Clockwork Diffusion: Efficient Generation With Model-Step
Distillation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8352-8361",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99514"}
@inproceedings{bb102799,
AUTHOR = "Phung, Q. and Ge, S.W. and Huang, J.B.",
TITLE = "Grounded Text-to-Image Synthesis with Attention Refocusing",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7932-7942",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT99515"}
Last update:Feb 26, 2026 at 10:58:24