{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:06:11Z","timestamp":1784228771509,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":95,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Artificial Intelligence Research Resource (NAIRR) Pilot","award":["NAIRR250199"],"award-info":[{"award-number":["NAIRR250199"]}]},{"name":"Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support","award":["CIS250012"],"award-info":[{"award-number":["CIS250012"]}]},{"name":"Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support","award":["CIS250816"],"award-info":[{"award-number":["CIS250816"]}]},{"name":"Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support","award":["CIS251188"],"award-info":[{"award-number":["CIS251188"]}]},{"name":"NVIDIA","award":["Academic Grant Program"],"award-info":[{"award-number":["Academic Grant Program"]}]},{"name":"National Science Foundation","award":["#2525287"],"award-info":[{"award-number":["#2525287"]}]},{"name":"National Science Foundation","award":["#2404385"],"award-info":[{"award-number":["#2404385"]}]},{"name":"National Science Foundation","award":["#2414227"],"award-info":[{"award-number":["#2414227"]}]},{"name":"National Science Foundation","award":["#2340254"],"award-info":[{"award-number":["#2340254"]}]},{"name":"National Science Foundation","award":["#2312102"],"award-info":[{"award-number":["#2312102"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#2331878"],"award-info":[{"award-number":["#2331878"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811122","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5163-6484","authenticated-orcid":false,"given":"Wei","family":"Cao","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2082-641X","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9577-5276","authenticated-orcid":false,"given":"Fengrui","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4982-9630","authenticated-orcid":false,"given":"Yulun","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1858-4257","authenticated-orcid":false,"given":"Yingying","family":"Li","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7984-266X","authenticated-orcid":false,"given":"Shenlong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6865-1325","authenticated-orcid":false,"given":"Ning","family":"Yu","sequence":"additional","affiliation":[{"name":"Eyeline Labs, Los Angeles, California, USA and Netflix, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5316-3028","authenticated-orcid":false,"given":"Yaoyao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Ronald\u00a0T Azuma. 1997. A survey of augmented reality. Presence: teleoperators & virtual environments 6 4 (1997) 355\u2013385.","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"e_1_3_3_2_3_1","unstructured":"Sherwin Bahmani Ivan Skorokhodov Aliaksandr Siarohin Willi Menapace Guocheng Qian Michael Vasilkovsky Hsin-Ying Lee Chaoyang Wang Jiaxu Zou Andrea Tagliasacchi et\u00a0al. 2024. Vd3d: Taming large video diffusion transformers for 3d camera control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.12781 (2024)."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"e_1_3_3_2_5_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_6_1","unstructured":"Wei Cao Marcel Hallgarten Tianyu Li Daniel Dauner Xunjiang Gu Caojun Wang Yakov Miron Marco Aiello Hongyang Li Igor Gilitschenski et\u00a0al. 2025. Pseudo-simulation for autonomous driving. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.04218 (2025)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01937"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"e_1_3_3_2_9_1","unstructured":"Hongyuan Chen Xingyu Chen Youjia Zhang Zexiang Xu and Anpei Chen. 2026. Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.14253 (2026)."},{"key":"e_1_3_3_2_10_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Chen Kaihua","year":"2025","unstructured":"Kaihua Chen, Tarasha Khurana, and Deva Ramanan. 2025. Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_2_11_1","first-page":"370","volume-title":"European conference on computer vision","author":"Chen Yuedong","year":"2024","unstructured":"Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, and Jianfei Cai. 2024. Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images. In European conference on computer vision. Springer, 370\u2013386."},{"key":"e_1_3_3_2_12_1","unstructured":"Xiang Fan Sharath Girish Vivek Ramanujan Chaoyang Wang Ashkan Mirzaei Petr Sushko Aliaksandr Siarohin Sergey Tulyakov and Ranjay Krishna. 2025. OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.10940 (2025)."},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"e_1_3_3_2_14_1","unstructured":"Google DeepMind. 2024. Veo. https:\/\/deepmind.google\/models\/veo\/. Accessed: 2024-11-05."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"e_1_3_3_2_16_1","unstructured":"Hao He Yinghao Xu Yuwei Guo Gordon Wetzstein Bo Dai Hongsheng Li and Ceyuan Yang. 2024. Cameractrl: Enabling camera control for text-to-video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02101 (2024)."},{"key":"e_1_3_3_2_17_1","unstructured":"Jixuan He Chieh\u00a0Hubert Lin Lu Qi and Ming-Hsuan Yang. 2025. Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.06715 (2025)."},{"key":"e_1_3_3_2_18_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_19_1","unstructured":"Chen Hou and Zhibo Chen. 2024. Training-free camera control for video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.10126 (2024)."},{"key":"e_1_3_3_2_20_1","unstructured":"Tao Hu Haoyang Peng Xiao Liu and Yuewen Ma. 2025. Ex-4d: Extreme viewpoint 4d video synthesis via depth watertight mesh. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.05554 (2025)."},{"key":"e_1_3_3_2_21_1","unstructured":"Jiahui Huang Qunjie Zhou Hesam Rabeti Aleksandr Korovko Huan Ling Xuanchi Ren Tianchang Shen Jun Gao Dmitry Slepichev Chen-Hsuan Lin et\u00a0al. 2025c. Vipe: Video pose engine for 3d geometric perception. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.10934 (2025)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Tianyu Huang Wangguandong Zheng Tengfei Wang Yuhao Liu Zhenwei Wang Junta Wu Jie Jiang Hui Li Rynson Lau Wangmeng Zuo et\u00a0al. 2025b. Voyager: Long-range and world-consistent video diffusion for explorable 3d scene generation. ACM Transactions on Graphics (TOG) 44 6 (2025) 1\u201315.","DOI":"10.1145\/3763330"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_2_24_1","unstructured":"Zhening Huang Hyeonho Jeong Xuelin Chen Yulia Gryaditskaya Tuanfeng\u00a0Y Wang Joan Lasenby and Chun-Hao Huang. 2025a. SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.25075 (2025)."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Lihan Jiang Yucheng Mao Linning Xu Tao Lu Kerui Ren Yichen Jin Xudong Xu Mulin Yu Jiangmiao Pang Feng Zhao et\u00a0al. 2025b. Anysplat: Feed-forward 3d gaussian splatting from unconstrained views. ACM Transactions on Graphics (TOG) 44 6 (2025) 1\u201316.","DOI":"10.1145\/3763326"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01921"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler George Drettakis et\u00a0al. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_29_1","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang et\u00a0al. 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_2_30_1","unstructured":"Yao-Chih Lee Zhoutong Zhang Jiahui Huang Jui-Hsien Wang Joon-Young Lee Jia-Bin Huang Eli Shechtman and Zhengqi Li. 2025. Generative Video Motion Editing with 3D Point Tracks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.02015 (2025)."},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00578"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Bing Li Cheng Zheng Wenxuan Zhu Jinjie Mai Biao Zhang Peter Wonka and Bernard Ghanem. 2024b. Vivid-zoo: Multi-view video generation with diffusion model. Advances in Neural Information Processing Systems 37 (2024) 62189\u201362222.","DOI":"10.52202\/079017-1987"},{"key":"e_1_3_3_2_33_1","unstructured":"Renjie Li Panwang Pan Bangbang Yang Dejia Xu Shijie Zhou Xuanyang Zhang Zeming Li Achuta Kadambi Zhangyang Wang Zhengzhong Tu et\u00a0al. 2024a. 4k4dgen: Panoramic 4d generation at 4k resolution. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.13527 (2024)."},{"key":"e_1_3_3_2_34_1","unstructured":"Ruilong Li Brent Yi Junchen Liu Hang Gao Yi Ma and Angjoo Kanazawa. 2025b. Cameras as relative positional encoding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.10496 (2025)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02673"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00849"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"crossref","unstructured":"Zhibing Li Mengchen Zhang Tong Wu Jing Tan Jiaqi Wang and Dahua Lin. 2025d. SS4D: Native 4D Generative Model via Structured Spacetime Latents. ACM Transactions on Graphics (TOG) 44 6 (2025) 1\u201312.","DOI":"10.1145\/3763302"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763836"},{"key":"e_1_3_3_2_40_1","unstructured":"Chenguo Lin Yuchen Lin Panwang Pan Yifan Yu Tao Hu Honglei Yan Katerina Fragkiadaki and Yadong Mu. 2025. Movies: Motion-aware 4d dynamic view synthesis in one second. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.10065 (2025)."},{"key":"e_1_3_3_2_41_1","unstructured":"Tianqi Liu Zhaoxi Chen Zihao Huang Shaocong Xu Saining Zhang Chongjie Ye Bohan Li Zhiguo Cao Wei Li Hao Zhao et\u00a0al. 2025. Light-X: Generative 4D Video Rendering with Camera and Illumination Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.05115 (2025)."},{"key":"e_1_3_3_2_42_1","unstructured":"Wei Liu Ziyu Chen Zizhang Li Yue Wang Hong-Xing Yu and Jiajun Wu. 2026. RealWonder: Real-Time Physical Action-Conditioned Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2603.05449 (2026)."},{"key":"e_1_3_3_2_43_1","unstructured":"Dongyue Lu Ao Liang Tianxin Huang Xiao Fu Yuyang Zhao Baorui Ma Liang Pan Wei Yin Lingdong Kong Wei\u00a0Tsang Ooi et\u00a0al. 2025. SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.26796 (2025)."},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763841"},{"key":"e_1_3_3_2_45_1","unstructured":"Zhanpeng Luo Haoxi Ran and Li Lu. 2025a. Instant4D: 4D Gaussian Splatting in Minutes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.01119 (2025)."},{"key":"e_1_3_3_2_46_1","unstructured":"Zhenxing Mi Yuxin Wang and Dan Xu. 2025. One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.18922 (2025)."},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_2_48_1","unstructured":"OpenAI. 2025. Sora: Creating video from text. https:\/\/openai.com\/index\/sora\/. Accessed: 2024-11-05."},{"key":"e_1_3_3_2_49_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_3_2_51_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_2_52_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et\u00a0al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00714 (2024)."},{"key":"e_1_3_3_2_53_1","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:https:\/\/arXiv.org\/abs\/2312.17142 (2023)."},{"key":"e_1_3_3_2_54_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan et\u00a0al. 2024. Grounded sam: Assembling open-world models for diverse visual tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.14159 (2024)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Junyoung Seo Kazumi Fukuda Takashi Shibuya Takuya Narihira Naoki Murata Shoukang Hu Chieh-Hsin Lai Seungryong Kim and Yuki Mitsufuji. 2024. Genwarp: Single image to novel views with semantic-preserving generative warping. Advances in Neural Information Processing Systems 37 (2024) 80220\u201380243.","DOI":"10.52202\/079017-2550"},{"key":"e_1_3_3_2_57_1","unstructured":"Chenxi Song Yanming Yang Tong Zhao Ruibo Li and Chi Zhang. 2025. Worldforge: Unlocking emergent 3d\/4d generation in video diffusion model via training-free guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.15130 (2025)."},{"key":"e_1_3_3_2_58_1","unstructured":"Edgar Sucar Eldar Insafutdinov Zihang Lai and Andrea Vedaldi. 2026. V-DPM: 4D Video Reconstruction with Dynamic Point Maps. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.09499 (2026)."},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"crossref","unstructured":"Jiapeng Tang Wei Cao Biao Zhang Chang Luo Yaoyao Liu and Matthias Nie\u00dfner. 2026. Motion2VecSets: Non-Rigid Shape Reconstruction and Tracking with 4D Latent Set Diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence (2026).","DOI":"10.1109\/TPAMI.2026.3680779"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00722"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01641"},{"key":"e_1_3_3_2_63_1","unstructured":"Fengrui Tian Yueqi Duan Angtian Wang Jianfei Guo and Shaoyi Du. 2024. Semantic flow: Learning semantic field of dynamic scenes from monocular videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.05163 (2024)."},{"key":"e_1_3_3_2_64_1","unstructured":"Thomas Unterthiner Sjoerd Van\u00a0Steenkiste Karol Kurach Rapha\u00ebl Marinier Marcin Michalski and Sylvain Gelly. 2019. FVD: A new metric for video generation. (2019)."},{"key":"e_1_3_3_2_65_1","first-page":"313","volume-title":"European Conference on Computer Vision","author":"Van\u00a0Hoorick Basile","year":"2024","unstructured":"Basile Van\u00a0Hoorick, Rundi Wu, Ege Ozguroglu, Kyle Sargent, Ruoshi Liu, Pavel Tokmakov, Achal Dave, Changxi Zheng, and Carl Vondrick. 2024. Generative camera dolly: Extreme monocular dynamic novel view synthesis. In European Conference on Computer Vision. Springer, 313\u2013331."},{"key":"e_1_3_3_2_66_1","unstructured":"Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng et\u00a0al. 2025a. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 3 4 (2025) 6."},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00901"},{"key":"e_1_3_3_2_69_1","unstructured":"Yiming Wang Qihang Zhang Shengqu Cai Tong Wu Jan Ackermann Zhengfei Kuang Yang Zheng Frano Raji\u010d Siyu Tang and Gordon Wetzstein. 2025d. BulletTime: Decoupled Control of Time and Camera Pose for Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.05076 (2025)."},{"key":"e_1_3_3_2_70_1","unstructured":"Yifan Wang Jianjun Zhou Haoyi Zhu Wenzheng Chang Yang Zhou Zizun Li Junyi Chen Jiangmiao Pang Chunhua Shen and Tong He. 2025e. \u03c03: Scalable Permutation-Equivariant Visual Geometry Learning. arXiv e-prints (2025) arXiv\u20132507."},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"e_1_3_3_2_72_1","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Sheng-ming Yin Shuai Bai Xiao Xu Yilei Chen et\u00a0al. 2025b. Qwen-image technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.02324 (2025)."},{"key":"e_1_3_3_2_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"e_1_3_3_2_74_1","unstructured":"Zeqi Xiao Wenqi Ouyang Yifan Zhou Shuai Yang Lei Yang Jianlou Si and Xingang Pan. 2024. Trajectory attention for fine-grained video motion control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.19324 (2024)."},{"key":"e_1_3_3_2_75_1","unstructured":"Yiming Xie Chun-Han Yao Vikram Voleti Huaizu Jiang and Varun Jampani. 2024. Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.17470 (2024)."},{"key":"e_1_3_3_2_76_1","unstructured":"Yuxue Yang Lue Fan Ziqi Shi Junran Peng Feng Wang and Zhaoxiang Zhang. 2026. NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.00393 (2026)."},{"key":"e_1_3_3_2_77_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06072 (2024)."},{"key":"e_1_3_3_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01231"},{"key":"e_1_3_3_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00112"},{"key":"e_1_3_3_2_80_1","unstructured":"Meng You Zhiyu Zhu Hui Liu and Junhui Hou. 2024. Nvs-solver: Video diffusion model as zero-shot novel view synthesizer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.15364 (2024)."},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00017"},{"key":"e_1_3_3_2_82_1","unstructured":"Wangbo Yu Jinbo Xing Li Yuan Wenbo Hu Xiaoyu Li Zhipeng Huang Xiangjun Gao Tien-Tsin Wong Ying Shan and Yonghong Tian. 2024. Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02048 (2024)."},{"key":"e_1_3_3_2_83_1","unstructured":"Yu Yuan Tharindu Wickremasinghe Zeeshan Nadir Xijun Wang Yiheng Chi and Stanley\u00a0H Chan. 2025. SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.03350 (2025)."},{"key":"e_1_3_3_2_84_1","first-page":"163","volume-title":"European Conference on Computer Vision","author":"Zeng Yifei","year":"2024","unstructured":"Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, and Yao Yao. 2024. Stag4d: Spatial-temporal anchored generative 4d gaussians. In European Conference on Computer Vision. Springer, 163\u2013179."},{"key":"e_1_3_3_2_85_1","unstructured":"Jiahao Zhan Zizhang Li Hong-Xing Yu and Jiajun Wu. 2026. PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.04876 (2026)."},{"key":"e_1_3_3_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00197"},{"key":"e_1_3_3_2_87_1","unstructured":"Hao Zhang Chun-Han Yao Simon Donn\u00e9 Narendra Ahuja and Varun Jampani. 2025d. Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.10687 (2025)."},{"key":"e_1_3_3_2_88_1","unstructured":"Junyi Zhang Charles Herrmann Junhwa Hur Varun Jampani Trevor Darrell Forrester Cole Deqing Sun and Ming-Hsuan Yang. 2024. Monst3r: A simple approach for estimating geometry in the presence of motion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.03825 (2024)."},{"key":"e_1_3_3_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02580"},{"key":"e_1_3_3_2_91_1","unstructured":"Yanran Zhang Ziyi Wang Wenzhao Zheng Zheng Zhu Jie Zhou and Jiwen Lu. 2025b. Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.05044 (2025)."},{"key":"e_1_3_3_2_92_1","unstructured":"Sixiao Zheng Minghao Yin Wenbo Hu Xiaoyu Li Ying Shan and Yanwei Fu. 2026. VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.05138 (2026)."},{"key":"e_1_3_3_2_93_1","unstructured":"Hongkuan Zhou Wei Cao Aifen Sui and Zhenshan Bing. 2023. What Matters to Enhance Traffic Rule Compliance of Imitation Learning for End-to-End Autonomous Driving. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.07808 (2023)."},{"key":"e_1_3_3_2_94_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-94575-5_7"},{"key":"e_1_3_3_2_95_1","unstructured":"Kaichen Zhou Yuhan Wang Grace Chen Xinhai Chang Gaspard Beaudouin Fangneng Zhan Paul\u00a0Pu Liang and Mengyu Wang. 2025b. Page-4d: Disentangled pose and geometry estimation for 4d perception. arXiv e-prints (2025) arXiv\u20132510."},{"key":"e_1_3_3_2_96_1","unstructured":"Ruijie Zhu Jiahao Lu Wenbo Hu Xiaoguang Han Jianfei Cai Ying Shan and Chuanxia Zheng. 2026. MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.08961 (2026)."}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3799902.3811122","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:26:39Z","timestamp":1784226399000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":95,"alternative-id":["10.1145\/3799902.3811122","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811122","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}