{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T03:25:27Z","timestamp":1783740327944,"version":"3.55.0"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02372","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25571-25582","source":"Crossref","is-referenced-by-count":2,"title":["Free4D: Tuning-Free 4D Scene Generation with Spatial-Temporal Consistency"],"prefix":"10.1109","author":[{"given":"Tianqi","family":"Liu","sequence":"first","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxi","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,S-Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangcong","family":"Wang","sequence":"additional","affiliation":[{"name":"Great Bay University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoukang","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,S-Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liao","family":"Shen","sequence":"additional","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,S-Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,S-Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning representations and generative models for 3d point clouds","volume-title":"6 th International Conference on Learning Representations","author":"Achlioptas","year":"2018"},{"key":"ref2","article-title":"Stochastic variational video prediction","volume-title":"6th International Conference on Learning Representations","author":"Babaeizadeh","year":"2018"},{"key":"ref3","article-title":"Fitvid: Overfitting in pixel-level video prediction","author":"Babaeizadeh","year":"2021","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref5","article-title":"Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2024","journal-title":"CoRR, abs\/2412.07760"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00513"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321857"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02475"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"ref12","article-title":"Adversarial video generation on complex datasets","author":"Clark","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"10","article-title":"Stochastic video generation with a learned prior","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Denton","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref16","first-page":"7","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Guo","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2027"},{"key":"ref18","article-title":"Latent video diffusion models for highfidelity video generation with arbitrary lengths","author":"He","year":"2022","journal-title":"CoRR, abs\/2211.13221"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models. CoRR, abs\/2210.02303"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref22","first-page":"1","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hong","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref26","first-page":"6","article-title":"Video pixel networks","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Kalchbrenner","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","first-page":"10","volume-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","volume":"38","author":"Kuang","year":"2024"},{"key":"ref29","first-page":"26","article-title":"Videoflow: A conditional flow-based model for stochastic video generation","volume-title":"8th International Conference on Learning Representations","author":"Kumar","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_37"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref34","article-title":"Videofusion: Decomposed diffusion models for high-quality video generation","author":"Luo","year":"2023","journal-title":"CoRR, abs\/2303.08320"},{"key":"ref35","first-page":"2","article-title":"Deep multi-scale video prediction beyond mean square error","volume-title":"4th International Conference on Learning Representations ICLR 2016, San Juan, Puerto Rico","author":"Mathieu","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00385"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02615-z"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00025"},{"key":"ref42","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref44","article-title":"Bringing objects to life: 4d generation from 3d objects","author":"Rahamim","year":"2024","journal-title":"CoRR, abs\/2412.20422"},{"key":"ref45","article-title":"Video (language) modeling: a baseline for generative models of natural videos","author":"Ranzato","year":"2014","journal-title":"CoRR, abs\/1412.6604"},{"key":"ref46","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"56828","article-title":"L4gm: Large 4d gaussian reconstruction model","volume":"37","author":"Ren","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","first-page":"1","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Singer","year":"2023"},{"key":"ref50","first-page":"23","article-title":"Text-to-4d dynamic scene generation","volume-title":"International Conference on Machine Learning","author":"Singer","year":"2023"},{"key":"ref51","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687681"},{"key":"ref53","article-title":"EG4D: explicit generation of 4d object without score distillation","author":"Sun","year":"2024","journal-title":"CoRR, abs\/2405.18132"},{"key":"ref54","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"CoRR, abs\/2411.04928"},{"key":"ref55","article-title":"KLING AI Team","year":"2024","journal-title":"Kling image-to-video model"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref57","first-page":"5","article-title":"Generating videos with scene dynamics","volume-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems","author":"Vondrick","year":"2016"},{"key":"ref58","article-title":"Vistadream: Sampling multiview consistent images for single-view scene reconstruction","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00777"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref65","author":"Wu","year":"2024","journal-title":"Cat4d: Create anything in 4d with multi-view video diffusion models. arXiv preprint arXiv:2411.18613"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01922"},{"key":"ref68","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"CoRR, abs\/2312.17225"},{"key":"ref69","first-page":"10","article-title":"4real: Towards photorealistic 4d scene generation via video diffusion models","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada","author":"Yu","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref71","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref73","article-title":"Animate124: Animating one image to 4 d dynamic scene","author":"Zhao","year":"2023","journal-title":"C o R R, abs\/2311.14603"},{"key":"ref74","article-title":"Genxd: Generating any 3d and 4d scenes","author":"Zhao","year":"2024","journal-title":"CoRR, abs\/2411.02319"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00697"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445498.pdf?arnumber=11445498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:51Z","timestamp":1777529691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02372","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}