@inproceedings{bb105100,
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#TT101800"}
@inproceedings{bb105101,
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#TT101801"}
@inproceedings{bb105102,
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#TT101802"}
@inproceedings{bb105103,
AUTHOR = "Zheng, G.C. 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#TT101803"}
@article{bb105104,
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#TT101804"}
@article{bb105105,
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#TT101805"}
@article{bb105106,
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#TT101806"}
@article{bb105107,
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#TT101807"}
@article{bb105108,
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#TT101808"}
@article{bb105109,
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#TT101809"}
@article{bb105110,
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#TT101810"}
@article{bb105111,
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#TT101811"}
@article{bb105112,
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#TT101812"}
@article{bb105113,
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#TT101813"}
@article{bb105114,
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#TT101814"}
@article{bb105115,
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#TT101815"}
@inproceedings{bb105116,
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#TT101816"}
@article{bb105117,
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#TT101817"}
@article{bb105118,
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#TT101818"}
@article{bb105119,
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#TT101819"}
@article{bb105120,
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#TT101820"}
@article{bb105121,
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#TT101821"}
@article{bb105122,
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#TT101822"}
@inproceedings{bb105123,
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#TT101823"}
@inproceedings{bb105124,
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#TT101824"}
@inproceedings{bb105125,
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#TT101825"}
@inproceedings{bb105126,
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#TT101826"}
@inproceedings{bb105127,
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#TT101827"}
@inproceedings{bb105128,
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#TT101828"}
@inproceedings{bb105129,
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#TT101829"}
@inproceedings{bb105130,
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#TT101830"}
@inproceedings{bb105131,
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#TT101831"}
@inproceedings{bb105132,
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#TT101832"}
@inproceedings{bb105133,
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#TT101833"}
@inproceedings{bb105134,
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#TT101834"}
@inproceedings{bb105135,
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#TT101835"}
@inproceedings{bb105136,
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#TT101836"}
@inproceedings{bb105137,
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#TT101837"}
@inproceedings{bb105138,
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#TT101838"}
@inproceedings{bb105139,
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#TT101839"}
@inproceedings{bb105140,
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#TT101840"}
@inproceedings{bb105141,
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#TT101841"}
@inproceedings{bb105142,
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#TT101842"}
@inproceedings{bb105143,
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#TT101843"}
@inproceedings{bb105144,
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#TT101844"}
@inproceedings{bb105145,
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#TT101845"}
@inproceedings{bb105146,
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#TT101846"}
@inproceedings{bb105147,
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#TT101847"}
@article{bb105148,
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#TT101848"}
@inproceedings{bb105149,
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#TT101849"}
@article{bb105150,
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#TT101850"}
@article{bb105151,
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#TT101851"}
@inproceedings{bb105152,
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#TT101852"}
@inproceedings{bb105153,
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#TT101853"}
@inproceedings{bb105154,
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#TT101854"}
@inproceedings{bb105155,
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#TT101855"}
@inproceedings{bb105156,
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#TT101856"}
@inproceedings{bb105157,
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#TT101857"}
@inproceedings{bb105158,
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#TT101858"}
@inproceedings{bb105159,
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#TT101859"}
@inproceedings{bb105160,
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#TT101860"}
@inproceedings{bb105161,
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#TT101861"}
@inproceedings{bb105162,
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#TT101862"}
@inproceedings{bb105163,
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#TT101863"}
@inproceedings{bb105164,
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#TT101864"}
@inproceedings{bb105165,
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#TT101865"}
@inproceedings{bb105166,
AUTHOR = "Yang, B.B. and Luo, Y. and Chen, Z.L. and Wang, G.R. and Liang, X.D. and Lin, L.",
TITLE = "LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22612-22622",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101866"}
@inproceedings{bb105167,
AUTHOR = "Levi, E. and Brosh, E. and Mykhailych, M. and Perez, M.",
TITLE = "DLT: Conditioned layout generation with Joint Discrete-Continuous
Diffusion Layout Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2106-2115",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101867"}
@inproceedings{bb105168,
AUTHOR = "Couairon, G. and Careil, M. and Cord, M. and Lathuiliere, S. and Verbeek, J.",
TITLE = "Zero-shot spatial layout conditioning for text-to-image diffusion
models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2174-2183",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101868"}
@inproceedings{bb105169,
AUTHOR = "Chai, S. and Zhuang, L.S. and Yan, F.Y.",
TITLE = "LayoutDM: Transformer-based Diffusion Model for Layout Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18349-18358",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101869"}
@inproceedings{bb105170,
AUTHOR = "Hui, M. and Zhang, Z.Z. and Zhang, X.Y. and Xie, W.X. and Wang, Y.W. and Lu, Y.",
TITLE = "Unifying Layout Generation with a Decoupled Diffusion Model",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1942-1951",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101870"}
@inproceedings{bb105171,
AUTHOR = "Zheng, G.C. and Zhou, X.P. and Li, X.W. and Qi, Z.A. and Shan, Y. and Li, X.",
TITLE = "LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image
Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22490-22499",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489laydift2i6.html#TT101871"}
@article{bb105172,
AUTHOR = "Lin, Z.H. and Lin, M. and Zhan, W. and Ji, R.R.",
TITLE = "AccDiffusion v2: Toward More Accurate Higher-Resolution Diffusion
Extrapolation",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "8351-8363",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101872"}
@inproceedings{bb105173,
AUTHOR = "Han, J. and Liu, J. and Jiang, Y. and Yan, B. and Zhang, Y.Q. and Yuan, Z.H. and Peng, B.Y. and Liu, X.B.",
TITLE = "Infinity?: Scaling Bitwise AutoRegressive Modeling for
High-Resolution Image Synthesis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15733-15744",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101873"}
@inproceedings{bb105174,
AUTHOR = "Jeong, J.H. and Han, S. and Kim, J. and Kim, S.J.",
TITLE = "Latent Space Super-Resolution for Higher-Resolution Image Generation
with Diffusion Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2355-2365",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101874"}
@inproceedings{bb105175,
AUTHOR = "Liu, Q.H. and Yin, X. and Yuille, A.L. and Brown, A. and Singh, M.",
TITLE = "Flowing from Words to Pixels: A Noise-Free Framework for
Cross-Modality Evolution",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2755-2765",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101875"}
@inproceedings{bb105176,
AUTHOR = "Choi, S. and Yun, J. and Park, J. and Choo, J.",
TITLE = "Disentangling Subject-Irrelevant Elements in Personalized
Text-to-Image Diffusion via Filtered Self-Distillation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9073-9082",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101876"}
@inproceedings{bb105177,
AUTHOR = "Wu, H.N. and Shen, S.C. and Hu, Q. and Zhang, X.Y. and Zhang, Y. and Wang, Y.F.",
TITLE = "MegaFusion: Extend Diffusion Models towards Higher-resolution Image
Generation without Further Tuning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "3944-3953",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101877"}
@inproceedings{bb105178,
AUTHOR = "Zhang, S. and Chen, Z.W. and Zhao, Z.Y. and Chen, Y.H. and Tang, Y. and Liang, J.J.",
TITLE = "Hidiffusion: Unlocking Higher-resolution Creativity and Efficiency in
Pretrained Diffusion Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LI: 145-161",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101878"}
@inproceedings{bb105179,
AUTHOR = "Huang, L.J. and Fang, R.Y. and Zhang, A.P. and Song, G.L. and Liu, S. and Liu, Y. and Li, H.S.",
TITLE = "FouriScale: A Frequency Perspective on Training-free High-resolution
Image Synthesis",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XII: 196-212",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101879"}
@inproceedings{bb105180,
AUTHOR = "Kim, G. and Kim, H. and Seo, H. and Kang, D.U. and Chun, S.Y.",
TITLE = "Beyondscene: Higher-resolution Human-centric Scene Generation with
Pretrained Diffusion",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXIV: 126-142",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101880"}
@inproceedings{bb105181,
AUTHOR = "Lin, Z.H. and Lin, M.B. and Zhao, M. and Ji, R.R.",
TITLE = "Accdiffusion: An Accurate Method for Higher-resolution Image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VI: 38-53",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101881"}
@inproceedings{bb105182,
AUTHOR = "Li, M.Y. and Cai, T. and Cao, J.X. and Zhang, Q.S. and Cai, H. and Bai, J.J. and Jia, Y.Q. and Li, K. and Han, S.",
TITLE = "DistriFusion: Distributed Parallel Inference for High-Resolution
Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7183-7193",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101882"}
@inproceedings{bb105183,
AUTHOR = "Du, R. and Chang, D.L. and Hospedales, T. and Song, Y.Z. and Ma, Z.Y.",
TITLE = "DemoFusion: Democratising High-Resolution Image Generation With No $$",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6159-6168",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101883"}
@inproceedings{bb105184,
AUTHOR = "Zhou, J.X. and Ding, T.Y. and Chen, T.Y. and Jiang, J.C. and Zharkov, I. and Zhu, Z.H. and Liang, L.",
TITLE = "DREAM: Diffusion Rectification and Estimation-Adaptive Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8342-8351",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101884"}
@inproceedings{bb105185,
AUTHOR = "Sun, H. and Li, W.B. and Liu, J.Z. and Chen, H.Y. and Pei, R.J. and Zou, X. and Yan, Y.L. and Yang, Y.",
TITLE = "CoSeR: Bridging Image and Language for Cognitive Super-Resolution",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "25868-25878",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101885"}
@inproceedings{bb105186,
AUTHOR = "Mei, K. and Delbracio, M. and Talebi, H. and Tu, Z.Z. and Patel, V.M. and Milanfar, P.",
TITLE = "CoDi: Conditional Diffusion Distillation for Higher-Fidelity and
Faster Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9048-9058",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101886"}
@inproceedings{bb105187,
AUTHOR = "Gandikota, K.V. and Chandramouli, P.",
TITLE = "Text-Guided Explorable Image Super-Resolution",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "25900-25911",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101887"}
@inproceedings{bb105188,
AUTHOR = "Zhao, T.C. and Ning, X.F. and Fang, T. and Liu, E. and Huang, G. and Lin, Z. and Yan, S.G. and Dai, G.H. and Wang, Y.",
TITLE = "Mixdq: Memory-efficient Few-step Text-to-image Diffusion Models with
Metric-decoupled Mixed Precision Quantization",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 285-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101888"}
@inproceedings{bb105189,
AUTHOR = "Parihar, R. and Sachidanand, V.S. and Mani, S. and Karmali, T. and Babu, R.V.",
TITLE = "Precisecontrol: Enhancing Text-to-image Diffusion Models with
Fine-grained Attribute Control",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXII: 469-487",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101889"}
@inproceedings{bb105190,
AUTHOR = "Gandikota, R. and Materzynska, J. and Zhou, T.R. and Torralba, A. and Bau, D.",
TITLE = "Concept Sliders: Lora Adaptors for Precise Control in Diffusion Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XL: 172-188",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489hresdift2i5.html#TT101890"}
@article{bb105191,
AUTHOR = "Naveen, S. and Ram Kiran, M.S. and Indupriya, M. and Manikanta, T.V. and Sudeep, P.V.",
TITLE = "Transformer models for enhancing AttnGAN based text to image
generation",
JOURNAL = IVC,
VOLUME = "115",
YEAR = "2021",
PAGES = "104284",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101891"}
@article{bb105192,
AUTHOR = "Dalmaz, O. and Yurt, M. and Cukur, T.",
TITLE = "ResViT: Residual Vision Transformers for Multimodal Medical Image
Synthesis",
JOURNAL = MedImg,
VOLUME = "41",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "2598-2614",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101892"}
@article{bb105193,
AUTHOR = "Zhang, X. and Jiao, W.T. and Wang, B. and Tian, X.D.",
TITLE = "CT-GAN: A conditional Generative Adversarial Network of transformer
architecture for text-to-image",
JOURNAL = SP:IC,
VOLUME = "115",
YEAR = "2023",
PAGES = "116959",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101893"}
@article{bb105194,
AUTHOR = "Sortino, R. and Palazzo, S. and Rundo, F. and Spampinato, C.",
TITLE = "Transformer-based image generation from scene graphs",
JOURNAL = CVIU,
VOLUME = "233",
YEAR = "2023",
PAGES = "103721",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101894"}
@inproceedings{bb105195,
AUTHOR = "Sortino, R. and Palazzo, S. and Spampinato, C.",
TITLE = "Transforming Image Generation from Scene Graphs",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "4118-4124",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101895"}
@inproceedings{bb105196,
AUTHOR = "Wang, Z.C. and Ren, Q. and Wang, J.L. and Yan, C.G. and Jiang, C.J.",
TITLE = "Mush: Multi-scale Hierarchical Feature Extraction for Semantic Image
Synthesis",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "VII:185-201",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101896"}
@article{bb105197,
AUTHOR = "Wei, Z.P. and Chen, J.J. and Goldblum, M. and Wu, Z.X. and Goldstein, T. and Jiang, Y.G. and Davis, L.S.",
TITLE = "Towards Transferable Adversarial Attacks on Image and Video
Transformers",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "6346-6358",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101897"}
@article{bb105198,
AUTHOR = "Wei, Z.P. and Chen, J.J. and Wu, Z.X. and Jiang, Y.G.",
TITLE = "Adaptive Cross-Modal Transferable Adversarial Attacks From Images to
Videos",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3772-3783",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101898"}
@inproceedings{bb105199,
AUTHOR = "Wei, Z.P. and Chen, J.J. and Wu, Z.X. and Jiang, Y.G.",
TITLE = "Cross-Modal Transferable Adversarial Attacks from Images to Videos",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15044-15053",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT101899"}
Last update:Oct 8, 2026 at 11:03:09