{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T19:49:46Z","timestamp":1782244186316,"version":"3.54.5"},"reference-count":77,"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\/iccv51701.2025.01128","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12135-12146","source":"Crossref","is-referenced-by-count":1,"title":["Synthetic Video Enhances Physical Fidelity in Video Synthesis"],"prefix":"10.1109","author":[{"given":"Qi","family":"Zhao","sequence":"first","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Ni","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyu","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Cheng","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyan","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohan","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","year":"2024","journal-title":"Blender market"},{"key":"ref3","article-title":"Blending diverse physical priors with neural networks","author":"Ba","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref6","article-title":"Videophy: Evaluating physical commonsense for video generation","author":"Bansal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Physion: Evaluating physical prediction from vision in humans and machines","author":"Bear","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2303"},{"key":"ref9","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref11","article-title":"Visual physics: Discovering physical laws from videos","author":"Chari","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Videojam: Joint appearance-motion representations for enhanced motion generation in video models","author":"Chefer","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2021.11.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0106"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0403"},{"key":"ref17","article-title":"Movie gen: Swot analysis of meta\u2019s generative ai foundation model for transforming media generation, advertising, and entertainment industries","author":"Ehtesham","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","year":"2024","journal-title":"Metahuman"},{"key":"ref19","year":"2024","journal-title":"Unreal engine 5"},{"key":"ref20","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"In Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref21","article-title":"Boosting latent diffusion with flow matching","author":"Fischer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Fair diffusion: Instructing text-toimage generation models on fairness","author":"Friedrich","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","author":"Garrido","year":"2025","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref25","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref26","year":"2024","journal-title":"Veo2 - google deepmind"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref28","article-title":"Classifier-free diffusion guidance","volume-title":"In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref29","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00662-0"},{"key":"ref31","article-title":"How far is video generation from world model: A physical law perspective","author":"Kang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2588"},{"key":"ref34","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref35","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","year":"2024","journal-title":"Kling video model"},{"key":"ref38","article-title":"Videoflow: A conditional flow-based model for stochastic video generation","author":"Kumar","year":"2019","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_17"},{"key":"ref41","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Generative physical ai in vision: A survey","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00357"},{"key":"ref47","article-title":"Towards world simulator: Crafting physical commonsense-based benchmark for video generation","author":"Meng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","year":"2024","journal-title":"Digital twin catalog"},{"key":"ref49","article-title":"Do generative video models learn physical principles from watching videos?","author":"Motamed","year":"2025","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref51","year":"2024","journal-title":"Poly haven"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref54","year":"2024","journal-title":"Gen-3 alpha"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref57","article-title":"Seaweed-7b: Cost-effective training of video generation foundation model","author":"Seawead","year":"2025","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Urbanworld: An urban world model for 3d city generation","author":"Shang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref60","article-title":"Styledrop: Text-to-image generation in any style","volume-title":"In 37th Conference on Neural Information Processing Systems (NeurIPS)","author":"Sohn","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00940"},{"key":"ref62","year":"2024","journal-title":"Blender"},{"key":"ref63","article-title":"Worlddreamer: Towards general world models for video generation via predicting masked tokens","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Learning to see physics via visual deanimation","volume-title":"In Advances in Neural Information Processing Systems","author":"Wu","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00155"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01754"},{"key":"ref67","article-title":"Depth any video with scalable synthetic data","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref69","article-title":"Video as the new language for real-world decision making","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref72","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref74","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Epo: Hierarchical 11 m agents with environment preference optimization","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1548"}],"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\/11444774.pdf?arnumber=11444774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T19:42:13Z","timestamp":1782243733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01128","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}