{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:33Z","timestamp":1784268573637,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202014,62332002,62425101"],"award-info":[{"award-number":["62202014,62332002,62425101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755128","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"9763-9772","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3616-9120","authenticated-orcid":false,"given":"Haiyang","family":"Zhou","sequence":"first","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4387-8967","authenticated-orcid":false,"given":"Wangbo","family":"Yu","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China and Peng Cheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5148-1379","authenticated-orcid":false,"given":"Jiawen","family":"Guan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9034-279X","authenticated-orcid":false,"given":"Xinhua","family":"Cheng","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China and Peng Cheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-5588","authenticated-orcid":false,"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, Guangdong, China and Peng Cheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_3_2_1_4_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550454.3555447","article-title":"Text2light: Zero-shot text-driven hdr panorama generation","volume":"41","author":"Chen Zhaoxi","year":"2022","unstructured":"Zhaoxi Chen, Guangcong Wang, and Ziwei Liu. 2022. Text2light: Zero-shot text-driven hdr panorama generation. ACM Transactions on Graphics (TOG), Vol. 41, 6 (2022), 1-16.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_8_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Cheng Xinhua","year":"2024","unstructured":"Xinhua Cheng, Tianyu Yang, Jianan Wang, Yu Li, Lei Zhang, Jian Zhang, and Li Yuan. 2024. Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=O072Rc8uUy"},{"key":"e_1_3_2_1_9_1","volume-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes. arXiv preprint arXiv:2311.13384","author":"Chung Jaeyoung","year":"2023","unstructured":"Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee, and Kyoung Mu Lee. 2023. Luciddreamer: Domain-free generation of 3d gaussian splatting scenes. arXiv preprint arXiv:2311.13384 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32299"},{"key":"e_1_3_2_1_11_1","volume-title":"Diffusion360: Seamless 360 degree panoramic image generation based on diffusion models. arXiv preprint arXiv:2311.13141","author":"Feng Mengyang","year":"2023","unstructured":"Mengyang Feng, Jinlin Liu, Miaomiao Cui, and Xuansong Xie. 2023. Diffusion360: Seamless 360 degree panoramic image generation based on diffusion models. arXiv preprint arXiv:2311.13141 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=Fx2SbBgcte"},{"key":"e_1_3_2_1_13_1","unstructured":"Jonathan Ho William Chan Chitwan Saharia Jay Whang Ruiqi Gao Alexey Gritsenko Diederik P Kingma Ben Poole Mohammad Norouzi David J Fleet et al. 2022a. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_15_1","volume-title":"Video diffusion models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Tim Salimans, Alexey Gritsenko, William Chan, Mohammad Norouzi, and David J Fleet. 2022b. Video diffusion models. Advances in neural information processing systems, Vol. 35 (2022), 8633-8646."},{"key":"e_1_3_2_1_16_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_18_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Jiang Yanqin","year":"2024","unstructured":"Yanqin Jiang, Li Zhang, Jin Gao, Weiming Hu, and Yao Yao. 2024. Consistent4D: Consistent 360textdegree Dynamic Object Generation from Monocular Video. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=sPUrdFGepF"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_21_1","volume-title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Kondratyuk Dan","year":"2024","unstructured":"Dan Kondratyuk, Lijun Yu, Xiuye Gu, Jos\u00e9 Lezama, Jonathan Huang, Grant Schindler, Rachel Hornung, Vighnesh Birodkar, Jimmy Yan, Ming-Chang Chiu, Krishna Somandepalli, Hassan Akbari, Yair Alon, Yong Cheng, Joshua V. Dillon, Agrim Gupta, Meera Hahn, Anja Hauth, David Hendon, Alonso Martinez, David Minnen, Mikhail Sirotenko, Kihyuk Sohn, Xuan Yang, Hartwig Adam, Ming-Hsuan Yang, Irfan Essa, Huisheng Wang, David A. Ross, Bryan Seybold, and Lu Jiang. 2024. VideoPoet: A Large Language Model for Zero-Shot Video Generation. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net."},{"key":"e_1_3_2_1_22_1","unstructured":"Black Forest Labs. 2023. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_23_1","volume-title":"Vividdream: Generating 3d scene with ambient dynamics. arXiv preprint arXiv:2405.20334","author":"Lee Yao-Chih","year":"2024","unstructured":"Yao-Chih Lee, Yi-Ting Chen, Andrew Wang, Ting-Hsuan Liao, Brandon Y Feng, and Jia-Bin Huang. 2024. Vividdream: Generating 3d scene with ambient dynamics. arXiv preprint arXiv:2405.20334 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Li Renjie","year":"2025","unstructured":"Renjie Li, Panwang Pan, Bangbang Yang, Dejia Xu, Shijie Zhou, Xuanyang Zhang, Zeming Li, Achuta Kadambi, Zhangyang Wang, Zhengzhong Tu, and Zhiwen Fan. 2025. 4K4DGen: Panoramic 4D Generation at 4K Resolution. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=qxRoo7ULCo"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680801"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00446"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00576"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_3_2_1_32_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Liu Yuan","year":"2024","unstructured":"Yuan Liu, Cheng Lin, Zijiao Zeng, Xiaoxiao Long, Lingjie Liu, Taku Komura, and Wenping Wang. 2024. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=MN3yH2ovHb"},{"key":"e_1_3_2_1_33_1","volume-title":"Latte: Latent diffusion transformer for video generation. Transactions on Machine Learning Research","author":"Ma Xin","year":"2025","unstructured":"Xin Ma, Yaohui Wang, Xinyuan Chen, Gengyun Jia, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, and Yu Qiao. 2025. Latte: Latent diffusion transformer for video generation. Transactions on Machine Learning Research (2025)."},{"key":"e_1_3_2_1_34_1","first-page":"1173","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024","author":"Ma Yikun","year":"2024","unstructured":"Yikun Ma, Dandan Zhan, and Zhi Jin. 2024. FastScene: Text-Driven Fast Indoor 3D Scene Generation via Panoramic Gaussian Splatting. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024. ijcai.org, 1173-1181. https:\/\/www.ijcai.org\/proceedings\/2024\/130"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_36_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022","volume":"16804","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 16784-16804. https:\/\/proceedings.mlr.press\/v162\/nichol22a.html"},{"key":"e_1_3_2_1_37_1","volume-title":"Text2immersion: Generative immersive scene with 3d gaussians. arXiv preprint arXiv:2312.09242","author":"Ouyang Hao","year":"2023","unstructured":"Hao Ouyang, Kathryn Heal, Stephen Lombardi, and Tiancheng Sun. 2023. Text2immersion: Generative immersive scene with 3d gaussians. arXiv preprint arXiv:2312.09242 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"e_1_3_2_1_39_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Qian Guocheng","year":"2024","unstructured":"Guocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren, Aliaksandr Siarohin, Bing Li, Hsin-Ying Lee, Ivan Skorokhodov, Peter Wonka, Sergey Tulyakov, and Bernard Ghanem. 2024. Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=0jHkUDyEO9"},{"key":"e_1_3_2_1_40_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_41_1","volume-title":"Dreamgaussian4d: Generative 4d gaussian splatting. arXiv preprint arXiv:2312.17142","author":"Ren Jiawei","year":"2023","unstructured":"Jiawei Ren, Liang Pan, Jiaxiang Tang, Chi Zhang, Ang Cao, Gang Zeng, and Ziwei Liu. 2023. Dreamgaussian4d: Generative 4d gaussian splatting. arXiv preprint arXiv:2312.17142 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3762-3772","author":"Rey-Area Manuel","year":"2022","unstructured":"Manuel Rey-Area, Mingze Yuan, and Christian Richardt. 2022. 360monodepth: High-resolution 360deg monocular depth estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3762-3772."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_44_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3241212"},{"key":"e_1_3_2_1_46_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Shi Yichun","year":"2024","unstructured":"Yichun Shi, Peng Wang, Jianglong Ye, Long Mai, Kejie Li, and Xiao Yang. 2024. MVDream: Multi-view Diffusion for 3D Generation. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FUgrjq2pbB"},{"key":"e_1_3_2_1_47_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Singer Uriel","year":"2023","unstructured":"Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman. 2023. Make-A-Video: Text-to-Video Generation without Text-Video Data. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=nJfylDvgzlq"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00136"},{"key":"e_1_3_2_1_49_1","volume-title":"Imagine360: Immersive 360 video generation from perspective anchor. arXiv preprint arXiv:2412.03552","author":"Tan Jing","year":"2024","unstructured":"Jing Tan, Shuai Yang, Tong Wu, Jingwen He, Yuwei Guo, Ziwei Liu, and Dahua Lin. 2024. Imagine360: Immersive 360 video generation from perspective anchor. arXiv preprint arXiv:2412.03552 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"e_1_3_2_1_51_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Tang Jiaxiang","year":"2024","unstructured":"Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, and Gang Zeng. 2024. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=UyNXMqnN3c"},{"key":"e_1_3_2_1_52_1","volume-title":"NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations. arXiv preprint arXiv:2503.23162","author":"Tang Zhenyu","year":"2025","unstructured":"Zhenyu Tang, Chaoran Feng, Xinhua Cheng, Wangbo Yu, Junwu Zhang, Yuan Liu, Xiaoxiao Long, Wenping Wang, and Li Yuan. 2025. NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations. arXiv preprint arXiv:2503.23162 (2025)."},{"key":"e_1_3_2_1_53_1","volume-title":"Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571","author":"Wang Jiuniu","year":"2023","unstructured":"Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, and Shiwei Zhang. 2023b. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00660"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"e_1_3_2_1_56_1","volume-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Advances in neural information processing systems","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023a. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Advances in neural information processing systems, Vol. 36 (2023), 8406-8441."},{"key":"e_1_3_2_1_57_1","volume-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090","author":"Wu Haoning","year":"2023","unstructured":"Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, et al., 2023. Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"e_1_3_2_1_59_1","volume-title":"European Conference on Computer Vision. Springer, 399-417","author":"Xing Jinbo","year":"2024","unstructured":"Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, and Tien-Tsin Wong. 2024. Dynamicrafter: Animating open-domain images with video diffusion priors. In European Conference on Computer Vision. Springer, 399-417."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730643"},{"key":"e_1_3_2_1_61_1","volume-title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Yang Zhuoyi","year":"2025","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Yuxuan Zhang, Weihan Wang, Yean Cheng, Bin Xu, Xiaotao Gu, Yuxiao Dong, and Jie Tang. 2025b. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=LQzN6TRFg9"},{"key":"e_1_3_2_1_62_1","volume-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency. arXiv preprint arXiv:2312.17225","author":"Yin Yuyang","year":"2023","unstructured":"Yuyang Yin, Dejia Xu, Zhangyang Wang, Yao Zhao, and Yunchao Wei. 2023. 4dgen: Grounded 4d content generation with spatial-temporal consistency. arXiv preprint arXiv:2312.17225 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00559"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591555"},{"key":"e_1_3_2_1_67_1","volume-title":"Evagaussians: Event stream assisted gaussian splatting from blurry images. arXiv preprint arXiv:2405.20224","author":"Yu Wangbo","year":"2024","unstructured":"Wangbo Yu, Chaoran Feng, Jiye Tang, Jiashu Yang, Zhenyu Tang, Xu Jia, Yuchao Yang, Li Yuan, and Yonghong Tian. 2024b. Evagaussians: Event stream assisted gaussian splatting from blurry images. arXiv preprint arXiv:2405.20224 (2024)."},{"key":"e_1_3_2_1_68_1","volume-title":"Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:2409.02048","author":"Yu Wangbo","year":"2024","unstructured":"Wangbo Yu, Jinbo Xing, Li Yuan, Wenbo Hu, Xiaoyu Li, Zhipeng Huang, Xiangjun Gao, Tien-Tsin Wong, Ying Shan, and Yonghong Tian. 2024c. Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:2409.02048 (2024)."},{"key":"e_1_3_2_1_69_1","volume-title":"European Conference on Computer Vision. Springer, 258-274","author":"Yu Wangbo","year":"2024","unstructured":"Wangbo Yu, Li Yuan, Yan-Pei Cao, Xiangjun Gao, Xiaoyu Li, Wenbo Hu, Long Quan, Ying Shan, and Yonghong Tian. 2024d. Hifi-123: Towards high-fidelity one image to 3d content generation. In European Conference on Computer Vision. Springer, 258-274."},{"key":"e_1_3_2_1_70_1","first-page":"21236","article-title":"Chronomagic-bench: A benchmark for metamorphic evaluation of text-to-time-lapse video generation","volume":"37","author":"Yuan Shenghai","year":"2024","unstructured":"Shenghai Yuan, Jinfa Huang, Yongqi Xu, Yaoyang Liu, Shaofeng Zhang, Yujun Shi, Rui-Jie Zhu, Xinhua Cheng, Jiebo Luo, and Li Yuan. 2024. Chronomagic-bench: A benchmark for metamorphic evaluation of text-to-time-lapse video generation. Advances in Neural Information Processing Systems, Vol. 37 (2024), 21236-21270.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00607"},{"key":"e_1_3_2_1_72_1","volume-title":"European Conference on Computer Vision. Springer, 303-320","author":"Zhang Junwu","year":"2024","unstructured":"Junwu Zhang, Zhenyu Tang, Yatian Pang, Xinhua Cheng, Peng Jin, Yida Wei, Xing Zhou, Munan Ning, and Li Yuan. 2024a. Repaint123: Fast and high-quality one image to 3d generation with progressive controllable repainting. In European Conference on Computer Vision. Springer, 303-320."},{"key":"e_1_3_2_1_73_1","volume-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint arXiv:2311.04145","author":"Zhang Shiwei","year":"2023","unstructured":"Shiwei Zhang, Jiayu Wang, Yingya Zhang, Kang Zhao, Hangjie Yuan, Zhiwu Qin, Xiang Wang, Deli Zhao, and Jingren Zhou. 2023. I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint arXiv:2311.04145 (2023)."},{"key":"e_1_3_2_1_74_1","volume-title":"Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018","author":"Zhou Daquan","year":"2022","unstructured":"Daquan Zhou, Weimin Wang, Hanshu Yan, Weiwei Lv, Yizhe Zhu, and Jiashi Feng. 2022. Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)."},{"key":"e_1_3_2_1_75_1","volume-title":"Holodreamer: Holistic 3d panoramic world generation from text descriptions. arXiv preprint arXiv:2407.15187","author":"Zhou Haiyang","year":"2024","unstructured":"Haiyang Zhou, Xinhua Cheng, Wangbo Yu, Yonghong Tian, and Li Yuan. 2024a. Holodreamer: Holistic 3d panoramic world generation from text descriptions. arXiv preprint arXiv:2407.15187 (2024)."},{"key":"e_1_3_2_1_76_1","volume-title":"European Conference on Computer Vision. Springer, 324-342","author":"Zhou Shijie","year":"2024","unstructured":"Shijie Zhou, Zhiwen Fan, Dejia Xu, Haoran Chang, Pradyumna Chari, Tejas Bharadwaj, Suya You, Zhangyang Wang, and Achuta Kadambi. 2024b. Dreamscene360: Unconstrained text-to-3d scene generation with panoramic gaussian splatting. In European Conference on Computer Vision. Springer, 324-342."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:00:27Z","timestamp":1765310427000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":76,"alternative-id":["10.1145\/3746027.3755128","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755128","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}