@inproceedings{bb102800,
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#TT99516"}
@inproceedings{bb102801,
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#TT99517"}
@inproceedings{bb102802,
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#TT99518"}
@inproceedings{bb102803,
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#TT99519"}
@inproceedings{bb102804,
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#TT99520"}
@inproceedings{bb102805,
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#TT99521"}
@inproceedings{bb102806,
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#TT99522"}
@inproceedings{bb102807,
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#TT99523"}
@inproceedings{bb102808,
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#TT99524"}
@article{bb102809,
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#TT99525"}
@inproceedings{bb102810,
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#TT99526"}
@inproceedings{bb102811,
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#TT99527"}
@inproceedings{bb102812,
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#TT99528"}
@inproceedings{bb102813,
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#TT99529"}
@inproceedings{bb102814,
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#TT99530"}
@inproceedings{bb102815,
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#TT99531"}
@inproceedings{bb102816,
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#TT99532"}
@inproceedings{bb102817,
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#TT99533"}
@inproceedings{bb102818,
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#TT99534"}
@inproceedings{bb102819,
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#TT99535"}
@inproceedings{bb102820,
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#TT99536"}
@inproceedings{bb102821,
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#TT99537"}
@inproceedings{bb102822,
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#TT99538"}
@inproceedings{bb102823,
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#TT99539"}
@inproceedings{bb102824,
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#TT99540"}
@inproceedings{bb102825,
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#TT99541"}
@inproceedings{bb102826,
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#TT99542"}
@inproceedings{bb102827,
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#TT99543"}
@article{bb102828,
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#TT99544"}
@article{bb102829,
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#TT99545"}
@article{bb102830,
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#TT99546"}
@article{bb102831,
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#TT99547"}
@inproceedings{bb102832,
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#TT99548"}
@inproceedings{bb102833,
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#TT99549"}
@article{bb102834,
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#TT99550"}
@article{bb102835,
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#TT99551"}
@inproceedings{bb102836,
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#TT99552"}
@article{bb102837,
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#TT99553"}
@article{bb102838,
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#TT99554"}
@article{bb102839,
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#TT99555"}
@article{bb102840,
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#TT99556"}
@article{bb102841,
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#TT99557"}
@inproceedings{bb102842,
AUTHOR = "Wu, C.Y. and Chen, X.K. and Wu, Z.Y. and Ma, Y.Y. and Liu, X.C. and Pan, Z.Z. and Liu, W. and Xie, Z. and Yu, X.K. and Ruan, C. and Luo, P.",
TITLE = "Janus: Decoupling Visual Encoding for Unified Multimodal
Understanding and Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "12966-12977",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99558"}
@inproceedings{bb102843,
AUTHOR = "Zha, K.W. and Yu, L.J. and Fathi, A. and Ross, D.A. and Schmid, C. and Katabi, D. and Gu, X.",
TITLE = "Language-Guided Image Tokenization for Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15713-15722",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99559"}
@inproceedings{bb102844,
AUTHOR = "Tu, K.Y. and Huang, M.Q. and Chen, Z. and Mao, Z.D.",
TITLE = "A4A: Adapter for Adapter Transfer via All-for-All Mapping for
Cross-Architecture Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18476-18485",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99560"}
@inproceedings{bb102845,
AUTHOR = "Wang, H.J. and Byeon, W. and Xu, J.R. and Gu, J. and Cheung, K.C. and Wang, X.L. and Han, K. and Kautz, J. and Liu, S.",
TITLE = "Parallel Sequence Modeling via Generalized Spatial Propagation
Network",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4473-4483",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99561"}
@inproceedings{bb102846,
AUTHOR = "Deng, J.Y. and Wu, X. and Yang, Y.X. and Zhu, C.C. and Wang, S. and Wu, Z.Y.",
TITLE = "Acquire and then Adapt: Squeezing out Text-to-Image Model for Image
Restoration",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23195-23206",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99562"}
@inproceedings{bb102847,
AUTHOR = "Choudhury, Z.Z. and McCane, B. and Coffey, S.",
TITLE = "Medical Image Synthesis Using Autoencoder with Vision Transformer",
BOOKTITLE = IVCNZ24,
YEAR = "2024",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99563"}
@inproceedings{bb102848,
AUTHOR = "Tschannen, M. and Eastwood, C. and Mentzer, F.",
TITLE = "GIVT: Generative Infinite-vocabulary Transformers",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVII: 292-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99564"}
@inproceedings{bb102849,
AUTHOR = "Ni, Z. and Wang, Y.L. and Zhou, R.P. and Lu, R. and Guo, J.Y. and Hu, J.Y. and Liu, Z.Y. and Yao, Y. and Huang, G.",
TITLE = "Adanat: Exploring Adaptive Policy for Token-based Image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 302-319",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99565"}
@inproceedings{bb102850,
AUTHOR = "Xu, M. and Lin, M.Y. and Ren, Q. and Jia, S.",
TITLE = "Ssthyper: Sparse Spectral Transformer for Hyperspectral Image
Reconstruction",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "IV: 142-159",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99566"}
@inproceedings{bb102851,
AUTHOR = "Hatamizadeh, A. and Song, J.M. and Liu, G.L. and Kautz, J. and Vahdat, A.",
TITLE = "Diffit: Diffusion Vision Transformers for Image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VIII: 37-55",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99567"}
@inproceedings{bb102852,
AUTHOR = "Gu, Y.C. and Wang, X.T. and Ge, Y.X. and Shan, Y. and Shou, M.Z.",
TITLE = "Rethinking the Objectives of Vector-Quantized Tokenizers for Image
Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7631-7640",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99568"}
@inproceedings{bb102853,
AUTHOR = "Ni, Z.L. and Wang, Y.L. and Zhou, R.P. and Guo, J.Y. and Hu, J.Y. and Liu, Z.Y. and Song, S. and Yao, Y. and Huang, G.",
TITLE = "Revisiting Non-Autoregressive Transformers for Efficient Image
Synthesis",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7007-7016",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99569"}
@inproceedings{bb102854,
AUTHOR = "Zhao, Y.Q. and Zhao, Z. and Li, J. and Dong, S. and Gao, S.H.",
TITLE = "RoomDesigner: Encoding Anchor-latents for Style-consistent and
Shape-compatible Indoor Scene Generation",
BOOKTITLE = "3DV24",
YEAR = "2024",
PAGES = "1413-1423",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99570"}
@inproceedings{bb102855,
AUTHOR = "Cai, H. and Li, M. and Zhang, Q.S. and Liu, M.Y. and Han, S.",
TITLE = "Condition-Aware Neural Network for Controlled Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7194-7203",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99571"}
@inproceedings{bb102856,
AUTHOR = "Zheng, S. and Yuan, X.",
TITLE = "Unfolding Framework with Prior of Convolution-Transformer Mixture and
Uncertainty Estimation for Video Snapshot Compressive Imaging",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "12692-12703",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99572"}
@inproceedings{bb102857,
AUTHOR = "Cao, S.Y. and Yin, Y.Q. and Huang, L.H. and Liu, Y. and Zhao, X. and Zhao, D.L. and Huang, K.Q.",
TITLE = "Efficient-VQGAN: Towards High-Resolution Image Generation with
Efficient Vision Transformers",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7334-7343",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99573"}
@inproceedings{bb102858,
AUTHOR = "Yun, J. and Lee, S. and Park, M.H. and Choo, J.",
TITLE = "iColoriT: Towards Propagating Local Hints to the Right Region in
Interactive Colorization by Leveraging Vision Transformer",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1787-1796",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99574"}
@inproceedings{bb102859,
AUTHOR = "Lin, K.E. and Yen Chen, L. and Lai, W.S. and Lin, T.Y. and Shih, Y.C. and Ramamoorthi, R.",
TITLE = "Vision Transformer for NeRF-Based View Synthesis from a Single Input
Image",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "806-815",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99575"}
@inproceedings{bb102860,
AUTHOR = "Lezama, J. and Chang, H. and Jiang, L. and Essa, I.",
TITLE = "Improved Masked Image Generation with Token-Critic",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIII:70-86",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99576"}
@inproceedings{bb102861,
AUTHOR = "Kong, X. and Jiang, L. and Chang, H. and Zhang, H. and Hao, Y. and Gong, H.F. and Essa, I.",
TITLE = "BLT: Bidirectional Layout Transformer for Controllable Layout
Generation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XVII:474-490",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99577"}
@inproceedings{bb102862,
AUTHOR = "Kong, D. and Kong, K. and Kim, K. and Min, S.J. and Kang, S.J.",
TITLE = "Image-Adaptive Hint Generation via Vision Transformer for Outpainting",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "4029-4038",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99578"}
@inproceedings{bb102863,
AUTHOR = "Maharana, A. and Hannan, D. and Bansal, M.",
TITLE = "StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story
Continuation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:70-87",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99579"}
@inproceedings{bb102864,
AUTHOR = "Kim, T. and Song, G. and Lee, S. and Kim, S. and Seo, Y. and Lee, S. and Kim, S.H. and Lee, H.L. and Bae, K.",
TITLE = "L-Verse: Bidirectional Generation Between Image and Text",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16505-16515",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99580"}
@inproceedings{bb102865,
AUTHOR = "Wang, J.A. and Lu, G.S. and Xu, H. and Li, Z.G. and Xu, C.J. and Fu, Y.W.",
TITLE = "ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise
Semantic Alignment and Generation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10697-10707",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99581"}
@inproceedings{bb102866,
AUTHOR = "Liu, Z.Z. and Wang, Y. and Qi, X.J. and Fu, C.W.",
TITLE = "Towards Implicit Text-Guided 3D Shape Generation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17875-17885",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99582"}
@inproceedings{bb102867,
AUTHOR = "Wu, F.X. and Liu, L. and Hao, F.S. and He, F.X. and Cheng, J.",
TITLE = "Text-to-Image Synthesis based on Object-Guided Joint-Decoding
Transformer",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18092-18101",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99583"}
@inproceedings{bb102868,
AUTHOR = "Wang, X.P. and Yeshwanth, C. and Nießner, M.",
TITLE = "SceneFormer: Indoor Scene Generation with Transformers",
BOOKTITLE = "3DV21",
YEAR = "2021",
PAGES = "106-115",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99584"}
@inproceedings{bb102869,
AUTHOR = "Mariotti, O. and Aodha, O.M. and Bilen, H.",
TITLE = "ViewNet: Unsupervised Viewpoint Estimation from Conditional
Generation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "10398-10408",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99585"}
@inproceedings{bb102870,
AUTHOR = "Ribeiro, L.S.F. and Bui, T. and Collomosse, J. and Ponti, M.",
TITLE = "Scene Designer:
A Unified Model for Scene Search and Synthesis from Sketch",
BOOKTITLE = SHE21,
YEAR = "2021",
PAGES = "2424-2433",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99586"}
@inproceedings{bb102871,
AUTHOR = "Yang, C.F. and Fan, W.C. and Yang, F.E. and Wang, Y.C.A.F.",
TITLE = "LayoutTransformer: Scene Layout Generation with Conceptual and
Spatial Diversity",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "3731-3740",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT99587"}
@article{bb102872,
AUTHOR = "Li, M. and Zhou, P. and Liu, J.W. and Keppo, J. and Lin, M. and Yan, S.C. and Xu, X.Y.",
TITLE = "Instant3D: Instant Text-to-3D Generation",
JOURNAL = IJCV,
VOLUME = "132",
YEAR = "2024",
NUMBER = "10",
MONTH = "October",
PAGES = "4456-4472",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99588"}
@article{bb102873,
AUTHOR = "Xu, X.Y. and Yan, S.C. and Lin, M. and Keppo, J. and Liu, J.W. and Zhou, P. and Li, M.",
TITLE = "Instant3D: Instant Text-to-3D Generation",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "509-509",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99588"}
@article{bb102874,
AUTHOR = "Nie, W.Z. and Chen, R.D. and Wang, W.J. and Lepri, B. and Sebe, N.",
TITLE = "T2TD: Text-3D Generation Model Based on Prior Knowledge Guidance",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "172-189",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99589"}
@article{bb102875,
AUTHOR = "Ye, Z. and Liu, Y. and Peng, Y.X.",
TITLE = "MAAN: Memory-Augmented Auto-Regressive Network for Text-Driven 3D
Indoor Scene Generation",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "11057-11069",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99590"}
@article{bb102876,
AUTHOR = "Luo, X.Z. and Zhao, H.T. and Liu, Y.P. and Liu, N.N. and Chen, J. and Yang, H. and Pan, J.",
TITLE = "A High-Precision Virtual Central Projection Image Generation Method
for an Aerial Dual-Camera",
JOURNAL = RS,
VOLUME = "17",
YEAR = "2025",
NUMBER = "4",
PAGES = "683",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99591"}
@article{bb102877,
AUTHOR = "Di, D.L. and Yang, J.H. and Luo, C.F. and Xue, Z. and Chen, W. and Yang, X. and Gao, Y.",
TITLE = "Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "2886-2909",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99592"}
@article{bb102878,
AUTHOR = "Huang, S.Y. and Huang, C.P. and Chang, K.P. and Chou, Z.T. and Liu, I.J. and Wang, Y.C.A.F.",
TITLE = "Learning Shape-Color Diffusion Priors for Text-Guided 3D Object
Generation",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "3294-3306",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99593"}
@article{bb102879,
AUTHOR = "Yu, S.S. and Zhu, J.X. and Li, J.Q. and Li, X.C. and Wang, K. and Tu, J. and Guo, D.",
TITLE = "SceneDiffusion: Scene Generation Model Embedded with Spatial
Constraints",
JOURNAL = IJGI,
VOLUME = "14",
YEAR = "2025",
NUMBER = "7",
PAGES = "250",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99594"}
@article{bb102880,
AUTHOR = "Kim, J.Y. and Park, J. and Kong, K. and Kang, S.J.",
TITLE = "Programmable-Room: Interactive Textured 3D Room Meshes Generation
Empowered by Large Language Models",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "6358-6368",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99595"}
@article{bb102881,
AUTHOR = "Fu, K. and Duan, H.Y. and Zhang, Z.C. and Liu, X.H. and Min, X.K. and Wang, J. and Zhai, G.T.",
TITLE = "Multi-Dimensional Quality Assessment for Text-to-3D Assets:
Dataset and Model",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "8145-8159",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99596"}
@inproceedings{bb102882,
AUTHOR = "Zhou, M. and Myers Dean, J. and Gurari, D.",
TITLE = "PartStickers: Generating Parts of Objects for Rapid Prototyping",
BOOKTITLE = AIConGen25,
YEAR = "2025",
PAGES = "6281-6291",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99597"}
@inproceedings{bb102883,
AUTHOR = "Tam, H.I.I. and Pun, H.I.D. and Wang, A.T. and Chang, A.X. and Savva, M.",
TITLE = "SceneMotifCoder: Example-Driven Visual Program Learning for
Generating 3D Object Arrangements",
BOOKTITLE = "3DV25",
YEAR = "2025",
PAGES = "179-188",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99598"}
@inproceedings{bb102884,
AUTHOR = "Sinha, S. and Khan, M.S. and Usama, M. and Sam, S. and Stricker, D. and Ali, S.A. and Afzal, M.Z.",
TITLE = "MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity
Text-to-3D Content Creation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8105-8116",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99599"}
@inproceedings{bb102885,
AUTHOR = "Xiang, J.F. and Lv, Z. and Xu, S.C. and Deng, Y. and Wang, R.C. and Zhang, B. and Chen, D. and Tong, X. and Yang, J.",
TITLE = "Structured 3D Latents for Scalable and Versatile 3D Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "21469-21480",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99600"}
@inproceedings{bb102886,
AUTHOR = "Xu, Y.L. and Qu, H.X. and Liu, J. and Zhang, W.X. and Yang, X.",
TITLE = "CMMLoc: Advancing Text-to-PointCloud Localization with
Cauchy-Mixture-Model Based Framework",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6637-6647",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99601"}
@inproceedings{bb102887,
AUTHOR = "Edelstein, Y. and Patashnik, O. and Cohen Bar, D. and Zelnik Manor, L.",
TITLE = "Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis
and Manipulation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "21458-21468",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99602"}
@inproceedings{bb102888,
AUTHOR = "Hu, H.Z. and Yin, T.W. and Luan, F. and Hu, Y.W. and Tan, H. and Xu, Z.X. and Bi, S. and Tulsiani, S. and Zhang, K.",
TITLE = "Turbo3D: Ultra-fast Text-to-3D Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23668-23678",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99603"}
@inproceedings{bb102889,
AUTHOR = "Qin, Y.M. and Xu, Z. and Liu, Y.",
TITLE = "Apply Hierarchical-Chain-of-Generation to Complex Attributes
Text-to-3D Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18521-18530",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99604"}
@inproceedings{bb102890,
AUTHOR = "Chen, Y.W. and Lan, Y.S. and Zhou, S. and Wang, T.F. and Pan, X.G.",
TITLE = "SAR3D: Autoregressive 3D Object Generation and Understanding via
Multi-scale 3D VQVAE",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28371-28382",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99605"}
@inproceedings{bb102891,
AUTHOR = "Li, J.H. and Ma, W.J. and Li, X.Y. and Lou, Y.Z. and Zhou, G.C. and Zhou, X.D.",
TITLE = "CAD-Llama: Leveraging Large Language Models for Computer-Aided Design
Parametric 3D Model Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18563-18573",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99606"}
@inproceedings{bb102892,
AUTHOR = "Duggal, S. and Hu, Y.S. and Michel, O. and Kembhavi, A. and Freeman, W.T. and Smith, N.A. and Krishna, R. and Torralba, A. and Farhadi, A. and Ma, W.C.",
TITLE = "Eval3D: Interpretable and Fine-Grained Evaluation for 3D Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13326-13336",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99607"}
@inproceedings{bb102893,
AUTHOR = "Huang, I. and Bao, Y. and Truong, K. and Zhou, H. and Schmid, C. and Guibas, L.J. and Fathi, A.",
TITLE = "FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D
Object Placement",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13466-13476",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99608"}
@inproceedings{bb102894,
AUTHOR = "Chen, Z.X. and Tang, J.X. and Dong, Y.H. and Cao, Z. and Hong, F.Z. and Lan, Y.S. and Wang, T.F. and Xie, H.Z. and Wu, T. and Saito, S. and Pan, L. and Lin, D. and Liu, Z.W.",
TITLE = "3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive
Diffusion",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "26576-26586",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99609"}
@inproceedings{bb102895,
AUTHOR = "Nath, U. and Goel, R. and Jeon, E.S. and Kim, C. and Min, K. and Yang, Y.Z. and Yang, Y.Z. and Turaga, P.",
TITLE = "Deep Geometric Moments Promote Shape Consistency in Text-to-3D
Generation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4331-4341",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99610"}
@inproceedings{bb102896,
AUTHOR = "Attaiki, S. and Guerrero, P. and Ceylan, D. and Mitra, N.J. and Ovsjanikov, M.",
TITLE = "GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "3985-3995",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99611"}
@inproceedings{bb102897,
AUTHOR = "Mercier, A. and Nakhli, R. and Reddy, M. and Yasarla, R. and Cai, H. and Porikli, F.M. and Berger, G.",
TITLE = "HexaGen3D: StableDiffusion is One Step Away from Fast and Diverse
Text-to-3D Generation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "1247-1257",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99612"}
@inproceedings{bb102898,
AUTHOR = "Li, J. and Zhang, Z. and Yang, J.",
TITLE = "TP2O: Creative Text Pair-to-object Generation Using Balance
Swap-Sampling",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXII: 92-111",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99613"}
@inproceedings{bb102899,
AUTHOR = "Xu, Y.H. and Shi, Z.F. and Wang, Y.F. and Chen, H.S. and Yang, C. and Peng, S. and Shen, Y.J. and Wetzstein, G.",
TITLE = "GRM: Large Gaussian Reconstruction Model for Efficient 3D
Reconstruction and Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XV: 1-20",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489tx23d6.html#TT99614"}
Last update:Feb 26, 2026 at 10:58:24