@inproceedings{bb103300,
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#TT100015"}
@inproceedings{bb103301,
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#TT100016"}
@inproceedings{bb103302,
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#TT100017"}
@inproceedings{bb103303,
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#TT100018"}
@inproceedings{bb103304,
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#TT100019"}
@inproceedings{bb103305,
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#TT100020"}
@inproceedings{bb103306,
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#TT100021"}
@inproceedings{bb103307,
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#TT100022"}
@inproceedings{bb103308,
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#TT100023"}
@inproceedings{bb103309,
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#TT100024"}
@inproceedings{bb103310,
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#TT100025"}
@inproceedings{bb103311,
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#TT100026"}
@inproceedings{bb103312,
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#TT100027"}
@inproceedings{bb103313,
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#TT100028"}
@inproceedings{bb103314,
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#TT100029"}
@inproceedings{bb103315,
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#TT100030"}
@inproceedings{bb103316,
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#TT100031"}
@inproceedings{bb103317,
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#TT100032"}
@inproceedings{bb103318,
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#TT100033"}
@inproceedings{bb103319,
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#TT100034"}
@inproceedings{bb103320,
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#TT100035"}
@inproceedings{bb103321,
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#TT100036"}
@inproceedings{bb103322,
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#TT100037"}
@inproceedings{bb103323,
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#TT100038"}
@inproceedings{bb103324,
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#TT100039"}
@inproceedings{bb103325,
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#TT100040"}
@inproceedings{bb103326,
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#TT100041"}
@inproceedings{bb103327,
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#TT100042"}
@inproceedings{bb103328,
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#TT100043"}
@inproceedings{bb103329,
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#TT100044"}
@inproceedings{bb103330,
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#TT100045"}
@inproceedings{bb103331,
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#TT100046"}
@inproceedings{bb103332,
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#TT100047"}
@inproceedings{bb103333,
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#TT100048"}
@inproceedings{bb103334,
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#TT100049"}
@inproceedings{bb103335,
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#TT100050"}
@inproceedings{bb103336,
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#TT100051"}
@inproceedings{bb103337,
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#TT100052"}
@inproceedings{bb103338,
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#TT100053"}
@inproceedings{bb103339,
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#TT100054"}
@inproceedings{bb103340,
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#TT100055"}
@inproceedings{bb103341,
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#TT100056"}
@inproceedings{bb103342,
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#TT100057"}
@article{bb103343,
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#TT100058"}
@inproceedings{bb103344,
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#TT100059"}
@article{bb103345,
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#TT100060"}
@article{bb103346,
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#TT100061"}
@inproceedings{bb103347,
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#TT100062"}
@inproceedings{bb103348,
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#TT100063"}
@inproceedings{bb103349,
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#TT100064"}
@inproceedings{bb103350,
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#TT100065"}
@inproceedings{bb103351,
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#TT100066"}
@inproceedings{bb103352,
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#TT100067"}
@inproceedings{bb103353,
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#TT100068"}
@inproceedings{bb103354,
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#TT100069"}
@inproceedings{bb103355,
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#TT100070"}
@inproceedings{bb103356,
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#TT100071"}
@inproceedings{bb103357,
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#TT100072"}
@inproceedings{bb103358,
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#TT100073"}
@inproceedings{bb103359,
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#TT100074"}
@inproceedings{bb103360,
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#TT100075"}
@inproceedings{bb103361,
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#TT100076"}
@inproceedings{bb103362,
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#TT100077"}
@inproceedings{bb103363,
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#TT100078"}
@inproceedings{bb103364,
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#TT100079"}
@inproceedings{bb103365,
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#TT100080"}
@inproceedings{bb103366,
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#TT100081"}
@article{bb103367,
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#TT100082"}
@inproceedings{bb103368,
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#TT100083"}
@inproceedings{bb103369,
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#TT100084"}
@inproceedings{bb103370,
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#TT100085"}
@inproceedings{bb103371,
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#TT100086"}
@inproceedings{bb103372,
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#TT100087"}
@inproceedings{bb103373,
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#TT100088"}
@inproceedings{bb103374,
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#TT100089"}
@inproceedings{bb103375,
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#TT100090"}
@inproceedings{bb103376,
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#TT100091"}
@inproceedings{bb103377,
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#TT100092"}
@inproceedings{bb103378,
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#TT100093"}
@inproceedings{bb103379,
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#TT100094"}
@inproceedings{bb103380,
AUTHOR = "Sun, H. and Li, W.B. and Liu, J.Z. and Chen, H.Y. and Pei, R. and Zou, X. and Yan, Y. 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#TT100095"}
@inproceedings{bb103381,
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#TT100096"}
@inproceedings{bb103382,
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#TT100097"}
@inproceedings{bb103383,
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#TT100098"}
@inproceedings{bb103384,
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#TT100099"}
@inproceedings{bb103385,
AUTHOR = "Gandikota, R. and Materzynska, J. and Zhou, T. 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#TT100100"}
@article{bb103386,
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#TT100101"}
@article{bb103387,
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#TT100102"}
@article{bb103388,
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#TT100103"}
@article{bb103389,
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#TT100104"}
@inproceedings{bb103390,
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#TT100105"}
@inproceedings{bb103391,
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#TT100106"}
@article{bb103392,
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#TT100107"}
@article{bb103393,
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#TT100108"}
@inproceedings{bb103394,
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#TT100109"}
@article{bb103395,
AUTHOR = "Bahani, M. and El Ouaazizi, A. and Maalmi, K.",
TITLE = "The effectiveness of T5, GPT-2, and BERT on text-to-image generation
task",
JOURNAL = PRL,
VOLUME = "173",
YEAR = "2023",
PAGES = "57-63",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT100110"}
@article{bb103396,
AUTHOR = "Su, S. and Zhu, J.C. and Gao, L.L. and Song, J.K.",
TITLE = "Utilizing Greedy Nature for Multimodal Conditional Image Synthesis in
Transformers",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "2354-2366",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT100111"}
@article{bb103397,
AUTHOR = "Li, Z. and Liu, F.",
TITLE = "Scalable video transformer for full-frame video prediction",
JOURNAL = CVIU,
VOLUME = "249",
YEAR = "2024",
PAGES = "104166",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT100112"}
@article{bb103398,
AUTHOR = "Cao, B. and Qi, G.L. and Zhao, J.M. and Zhu, P.F. and Hu, Q.H. and Gao, X.B.",
TITLE = "RTF: Recursive TransFusion for Multi-Modal Image Synthesis",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "1573-1587",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT100113"}
@article{bb103399,
AUTHOR = "Zheng, J.B. and Liu, D.Q. and Wang, C.Y. and Hu, M.H. and Yang, Z.P. and Ding, C.X. and Tao, D.C.",
TITLE = "MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal
Conditional Image Synthesis",
JOURNAL = IJCV,
VOLUME = "132",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "3537-3565",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT100114"}
Last update:May 3, 2026 at 17:51:13