{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:58Z","timestamp":1777865458500,"version":"3.51.4"},"reference-count":64,"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\/iccv51701.2025.00960","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10307-10317","source":"Crossref","is-referenced-by-count":0,"title":["How Far are AI-Generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach"],"prefix":"10.1109","author":[{"given":"Chirui","family":"Chang","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Lingnan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Hua","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Video Arena Leaderboard","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024","journal-title":"OpenAI"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"ref9","author":"Fan","year":"2024","journal-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1117\/12.473899"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref13","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02060"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref23","volume-title":"Kling ai","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657409"},{"key":"ref28","volume-title":"Dream machine","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01971"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref32","volume-title":"Hailuo ai","year":"2024"},{"key":"ref33","author":"Nichol","year":"2021","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref34","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref36","volume-title":"Pexels","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref38","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","volume-title":"Gen-3","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref44","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02658"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref48","author":"Selvaraju","year":"2016","journal-title":"Grad-cam: Why did you say that?"},{"key":"ref49","volume-title":"Vidu","year":"2024"},{"key":"ref50","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref52","author":"Unterthiner","year":"2019","journal-title":"Fvd: A new metric for video generation"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref54","author":"Wang","year":"2021","journal-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01922"},{"key":"ref59","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1814"},{"key":"ref61","author":"Zeng","year":"2024","journal-title":"The dawn of video generation: Preliminary explorations with sora-like models"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref63","first-page":"29835","article-title":"Ners: Neural reflectance surfaces for sparse-view 3d reconstruction in the wild","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref64","author":"Zhou","year":"2022","journal-title":"Magicvideo: Efficient video generation with latent diffusion models"}],"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\/11443481.pdf?arnumber=11443481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:59Z","timestamp":1777530959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00960","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}