@inproceedings{bb105000,
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#TT101700"}
@inproceedings{bb105001,
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#TT101701"}
@inproceedings{bb105002,
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#TT101702"}
@inproceedings{bb105003,
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#TT101703"}
@inproceedings{bb105004,
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#TT101704"}
@inproceedings{bb105005,
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#TT101705"}
@inproceedings{bb105006,
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#TT101706"}
@inproceedings{bb105007,
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#TT101707"}
@inproceedings{bb105008,
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#TT101708"}
@inproceedings{bb105009,
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#TT101709"}
@inproceedings{bb105010,
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#TT101710"}
@inproceedings{bb105011,
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#TT101711"}
@inproceedings{bb105012,
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#TT101712"}
@inproceedings{bb105013,
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#TT101713"}
@inproceedings{bb105014,
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#TT101714"}
@inproceedings{bb105015,
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#TT101715"}
@inproceedings{bb105016,
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#TT101716"}
@inproceedings{bb105017,
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#TT101717"}
@inproceedings{bb105018,
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#TT101718"}
@inproceedings{bb105019,
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#TT101719"}
@inproceedings{bb105020,
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#TT101720"}
@inproceedings{bb105021,
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#TT101721"}
@inproceedings{bb105022,
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#TT101722"}
@inproceedings{bb105023,
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#TT101723"}
@inproceedings{bb105024,
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#TT101724"}
@inproceedings{bb105025,
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#TT101725"}
@inproceedings{bb105026,
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#TT101726"}
@inproceedings{bb105027,
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#TT101727"}
@inproceedings{bb105028,
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#TT101728"}
@inproceedings{bb105029,
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#TT101729"}
@inproceedings{bb105030,
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#TT101730"}
@inproceedings{bb105031,
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#TT101731"}
@inproceedings{bb105032,
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#TT101732"}
@inproceedings{bb105033,
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#TT101733"}
@inproceedings{bb105034,
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#TT101734"}
@inproceedings{bb105035,
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#TT101735"}
@inproceedings{bb105036,
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#TT101736"}
@inproceedings{bb105037,
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#TT101737"}
@article{bb105038,
AUTHOR = "Sun, G. and Liang, W.Q. and Dong, J.H. and Li, J. and Ding, Z.M. and Cong, Y.",
TITLE = "Create Your World: Lifelong Text-to-Image Diffusion",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "6454-6470",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101738"}
@article{bb105039,
AUTHOR = "Verma, A. and Badal, T. and Bansal, A.",
TITLE = "Advancing Image Generation with Denoising Diffusion Probabilistic
Model and ConvNeXt-V2:
A novel approach for enhanced diversity and quality",
JOURNAL = CVIU,
VOLUME = "247",
YEAR = "2024",
PAGES = "104077",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101739"}
@article{bb105040,
AUTHOR = "Ren, J.X. and Liu, W.Z. and Chen, J. and Yin, S.X. and Tao, Y.",
TITLE = "Word2Scene: Efficient remote sensing image scene generation with only
one word via hybrid intelligence and low-rank representation",
JOURNAL = PandRS,
VOLUME = "218",
YEAR = "2024",
PAGES = "231-257",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101740"}
@article{bb105041,
AUTHOR = "Ridley, H. and Alcover Couso, R. and SanMiguel, J.C.",
TITLE = "Controlling semantics of diffusion-augmented data for unsupervised
domain adaptation",
JOURNAL = IET-CV,
VOLUME = "19",
YEAR = "2025",
NUMBER = "1",
PAGES = "e70002",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101741"}
@article{bb105042,
AUTHOR = "Wang, W.L. and Bao, J.M. and Zhou, W.G. and Chen, D.D. and Chen, D. and Yuan, L. and Li, H.Q.",
TITLE = "SinDiffusion: Learning a Diffusion Model from a Single Natural Image",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "3412-3423",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101742"}
@article{bb105043,
AUTHOR = "Kim, J. and Kang, J. and Kim, T. and Oh, H.",
TITLE = "SinWaveFusion: Learning a single image diffusion model in wavelet
domain",
JOURNAL = IVC,
VOLUME = "159",
YEAR = "2025",
PAGES = "105551",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101743"}
@article{bb105044,
AUTHOR = "Huang, Y.W. and Huang, H.M. and Zheng, H. and Li, Y.X. and Zheng, F. and Zhen, X.T. and Zheng, Y.F.",
TITLE = "Learning to Generalize Heterogeneous Representation for Cross-Modality
Image Synthesis via Multiple Domain Interventions",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "7",
MONTH = "July",
PAGES = "4727-4748",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101744"}
@article{bb105045,
AUTHOR = "Zhang, Z. and Zhang, S. and Shen, L. and Zhan, Y.B. and Luo, Y. and Hu, H. and Du, B. and Wen, Y.G. and Tao, D.C.",
TITLE = "Aligning Text-to-Image Diffusion Models With Constrained
Reinforcement Learning",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "9550-9562",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101745"}
@article{bb105046,
AUTHOR = "Zhang, Z. and Shen, L. and Zhang, S. and Ye, D. and Luo, Y. and Shi, M.J. and Shan, D.J. and Du, B. and Tao, D.C.",
TITLE = "Aligning Few-Step Diffusion Models With Dense Reward Difference
Learning",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "7",
MONTH = "July",
PAGES = "7375-7386",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101746"}
@article{bb105047,
AUTHOR = "Zhu, J.Y. and Ma, H.M. and Chen, J.S. and Yuan, J.",
TITLE = "DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image
Generation Using Limited Data",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "7012-7036",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101747"}
@article{bb105048,
AUTHOR = "Xiang, X. and Zhou, W.H. and Zhu, H.N. and Li, Y. and Dai, G.J. and Lin, L.",
TITLE = "EEG-driven natural image reconstruction with regional semantic
awareness",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112589",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101748"}
@article{bb105049,
AUTHOR = "Mao, Z.D. and Huang, M.Q. and Ding, F. and Liu, M.C. and He, Q. and Zhang, Y.D.",
TITLE = "RealCustom++: Representing Images as Real Textual Word for Real-Time
Customization",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "2078-2095",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101749"}
@inproceedings{bb105050,
AUTHOR = "Huang, M.Q. and Mao, Z.D. and Liu, M.C. and He, Q. and Zhang, Y.D.",
TITLE = "RealCustom: Narrowing Real Text Word for Real-Time Open-Domain
Text-to-Image Customization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7476-7485",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101750"}
@article{bb105051,
AUTHOR = "Ni, Z. and Wang, Y.L. and Hua, Y. and Zhou, R.P. and Guo, J.Y. and Song, J. and Zheng, B. and Huang, G.",
TITLE = "AdaGen: Learning Adaptive Policy for Image Synthesis",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "2695-2713",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101751"}
@article{bb105052,
AUTHOR = "Guo, J. and Chen, H.J. and Wang, Q.F. and Chen, Y. and Cheng, G.L. and Wu, F.Y. and Lim, E.G.",
TITLE = "EmoSENSE: Modeling Sentiment-Semantic Knowledge With Hierarchical
Reinforcement Learning for Emotional Image Generation",
JOURNAL = AffCom,
VOLUME = "17",
YEAR = "2026",
NUMBER = "2",
MONTH = "April",
PAGES = "1806-1822",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101752"}
@article{bb105053,
AUTHOR = "Fuest, M. and Ma, P. and Gui, M. and Schusterbauer, J. and Hu, V.T. and Ommer, B.",
TITLE = "Diffusion Models and Representation Learning: A Survey",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "7",
MONTH = "July",
PAGES = "7209-7228",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101753"}
@article{bb105054,
AUTHOR = "Wang, Y.B. and Hong, X.P. and Ma, Z.H. and Su, Z. and Zhang, J.P. and Huang, Z.W.",
TITLE = "Continual Conceptual Entity Learning for Text-to-Image Generative
Models",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "5785-5797",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101754"}
@article{bb105055,
AUTHOR = "Dubey, A. and Sharma, M. and Kancharla, P.",
TITLE = "Selective subspace unlearning for text to image diffusion models",
JOURNAL = PRL,
VOLUME = "207",
YEAR = "2026",
PAGES = "260-265",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101755"}
@article{bb105056,
AUTHOR = "Zhu, Y.F. and Wang, C.J. and Dong, X.H.",
TITLE = "UMDM-USG: A unified multi-view diffusion model for underwater scene
generation via cross-view representation alignment",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114232",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101756"}
@inproceedings{bb105057,
AUTHOR = "Song, J. and Choi, J.Y. and Baek, K. and Lee, S. and Park, D. and Yoon, S.",
TITLE = "DCText: Scheduled Attention Masking for Visual Text Generation via
Divide-and-Conquer Strategy",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "4305-4314",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101757"}
@inproceedings{bb105058,
AUTHOR = "Dong, S. and Shaheen, I. and Shen, M. and Mallick, R. and Bargal, S.A.",
TITLE = "ViSTA: Visual Storytelling using Multi-modal Adapters for
Text-to-Image Diffusion Models",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "12-21",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101758"}
@inproceedings{bb105059,
AUTHOR = "Hu, Z.J. and Zhang, F.D. and Chen, L. and Kuang, K. and Li, J.H. and Gao, K. and Xiao, J. and Wang, X. and Zhu, W.W.",
TITLE = "Towards Better Alignment: Training Diffusion Models with
Reinforcement Learning Against Sparse Rewards",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23604-23614",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101759"}
@inproceedings{bb105060,
AUTHOR = "Ye, Z. and Chen, Z.Y. and Li, T.C. and Huang, Z. and Luo, W.J. and Qi, G.J.",
TITLE = "Schedule On the Fly: Diffusion Time Prediction for Faster and Better
Image Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23412-23422",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101760"}
@inproceedings{bb105061,
AUTHOR = "Thakral, K. and Glaser, T. and Hassner, T. and Vatsa, M. and Singh, R.",
TITLE = "Fine-Grained Erasure in Text-To-Image Diffusion-Based Foundation
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9121-9130",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101761"}
@inproceedings{bb105062,
AUTHOR = "Jun, Y. and Park, J. and Choo, K. and Choi, T.E. and Hwang, S.J.",
TITLE = "Disentangling Disentangled Representations: Towards Improved Latent
Units via Diffusion Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "3559-3569",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101762"}
@inproceedings{bb105063,
AUTHOR = "Zhang, J.Y. and Zhou, Y.F. and Gu, J.X. and Wigington, C. and Yu, T. and Chen, Y.R. and Sun, T. and Zhang, R.",
TITLE = "ARTIST: Improving the Generation of Text-Rich Images with
Disentangled Diffusion Models and Large Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "1268-1278",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101763"}
@inproceedings{bb105064,
AUTHOR = "Butt, M.A. and Wang, K. and Vazquez Corral, J. and van de Weijer, J.",
TITLE = "ColorPeel: Color Prompt Learning with Diffusion Models via Color and
Shape Disentanglement",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VII: 456-472",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101764"}
@inproceedings{bb105065,
AUTHOR = "Zhang, D.J.H. and Xu, M. and Wu, J.Z.J. and Xue, C. and Zhang, W.Q. and Han, X.G. and Bai, S. and Shou, M.Z.",
TITLE = "Free-atm: Harnessing Free Attention Masks for Representation Learning
on Diffusion-generated Images",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XL: 465-482",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101765"}
@inproceedings{bb105066,
AUTHOR = "Hudson, D.A. and Zoran, D. and Malinowski, M. and Lampinen, A.K. and Jaegle, A. and McClelland, J.L. and Matthey, L. and Hill, F. and Lerchner, A.",
TITLE = "SODA: Bottleneck Diffusion Models for Representation Learning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23115-23127",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101766"}
@inproceedings{bb105067,
AUTHOR = "Miao, Z.C. and Wang, J. and Wang, Z. and Yang, Z.Y. and Wang, L.J. and Qiu, Q. and Liu, Z.C.",
TITLE = "Training Diffusion Models Towards Diverse Image Generation with
Reinforcement Learning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10844-10853",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101767"}
@inproceedings{bb105068,
AUTHOR = "Zhu, R. and Pan, Y.W. and Li, Y. and Yao, T. and Sun, Z.L. and Mei, T. and Chen, C.W.",
TITLE = "SD-DiT: Unleashing the Power of Self-Supervised Discrimination in
Diffusion Transformer*",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8435-8445",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101768"}
@inproceedings{bb105069,
AUTHOR = "Deng, F. and Wang, Q.F. and Wei, W. and Hou, T.B. and Grundmann, M.",
TITLE = "PRDP: Proximal Reward Difference Prediction for Large-Scale Reward
Finetuning of Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7423-7433",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101769"}
@inproceedings{bb105070,
AUTHOR = "Yu, Y.Y. and Liu, B.Z. and Zheng, C.X. and Xu, X.M. and He, S.F. and Zhang, H.D.",
TITLE = "Beyond Textual Constraints: Learning Novel Diffusion Conditions with
Fewer Examples",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7109-7118",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101770"}
@inproceedings{bb105071,
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/describe489leadift2i5.html#TT101771"}
@inproceedings{bb105072,
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/describe489leadift2i5.html#TT101772"}
@inproceedings{bb105073,
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/describe489leadift2i5.html#TT101773"}
@inproceedings{bb105074,
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/describe489leadift2i5.html#TT101774"}
@inproceedings{bb105075,
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/describe489leadift2i5.html#TT101775"}
@inproceedings{bb105076,
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/describe489leadift2i5.html#TT101776"}
@inproceedings{bb105077,
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/describe489leadift2i5.html#TT101777"}
@inproceedings{bb105078,
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/describe489leadift2i5.html#TT101778"}
@inproceedings{bb105079,
AUTHOR = "Ramasinghe, S. and Shevchenko, V. and Avraham, G. and Thalaiyasingam, A.",
TITLE = "Accept the Modality Gap: An Exploration in the Hyperbolic Space",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27253-27262",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489leadift2i5.html#TT101779"}
@inproceedings{bb105080,
AUTHOR = "Li, C. and Qi, Y. and Zeng, Q.T. 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/describe489leadift2i5.html#TT101780"}
@inproceedings{bb105081,
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/describe489leadift2i5.html#TT101781"}
@article{bb105082,
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#TT101782"}
@inproceedings{bb105083,
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#TT101783"}
@article{bb105084,
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#TT101784"}
@article{bb105085,
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#TT101785"}
@inproceedings{bb105086,
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#TT101786"}
@inproceedings{bb105087,
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#TT101787"}
@inproceedings{bb105088,
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#TT101788"}
@inproceedings{bb105089,
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#TT101789"}
@inproceedings{bb105090,
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#TT101790"}
@inproceedings{bb105091,
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#TT101791"}
@inproceedings{bb105092,
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#TT101792"}
@inproceedings{bb105093,
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#TT101793"}
@inproceedings{bb105094,
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#TT101794"}
@inproceedings{bb105095,
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#TT101795"}
@inproceedings{bb105096,
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#TT101796"}
@inproceedings{bb105097,
AUTHOR = "Gong, B. and Huang, S. and Feng, Y.T. and Zhang, S.W. and Li, Y. and Liu, Y.",
TITLE = "Check, Locate, Rectify: A Training-Free Layout Calibration System for
Text- to- Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6624-6634",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101797"}
@inproceedings{bb105098,
AUTHOR = "Shirakawa, T. and Uchida, S.",
TITLE = "NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on
Noise Cropping and Merging",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8921-8930",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101798"}
@inproceedings{bb105099,
AUTHOR = "Sueyoshi, K. and Matsubara, T.",
TITLE = "Predicated Diffusion: Predicate Logic-Based Attention Guidance for
Text-to-Image Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8651-8660",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101799"}
Last update:Sep 30, 2026 at 11:45:00