{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:48:44Z","timestamp":1779295724195,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.00498","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5242-5252","source":"Crossref","is-referenced-by-count":2,"title":["PhysSplat: Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Wuhan National Laboratory for Optoelectronics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyue","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xi'an Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongqiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),The Department of Systems Hub"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjiang","family":"Long","sequence":"additional","affiliation":[{"name":"Meta Reality Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0022-5096(95)00058-Q"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01537"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref6","article-title":"Palme: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"Proc. of Intl. Conf. on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00426"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2013.11.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1167\/13.8.9"},{"key":"ref10","first-page":"19740","author":"Haque","year":"2023","journal-title":"Instruct-nerf2nerf: Editing 3d scenes with instructions. In Proc. of IEEE Intl. Conf. on Computer Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.48"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201293"},{"key":"ref13","author":"Huang","year":"2024","journal-title":"DreamPhysics: Learning physical prop-erties of dynamic 3d gaussians with video diffusion priors. arXiv preprint arXiv:2406.01476"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3687939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"Proc. of Intl. Conf. on Machine Learning"},{"key":"ref20","article-title":"PAC- NeRF: Physics augmented continuum neural radiance fields for geometry-agnostic system identification","volume-title":"Proc. of International Conference on Learning Representations, 2023. 2","author":"Li"},{"key":"ref21","article-title":"Physics3D: Learning physical properties of 3d gaussians via video diffusion","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3658184"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_1"},{"key":"ref27","article-title":"Feature splatting: Language-driven physics-based scene synthesis and editing","volume-title":"arXiv preprint","author":"Qiu","year":"2024"},{"key":"ref28","author":"Raafat","year":"2023","journal-title":"BlenderNeRF"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"Proc. of Intl. Conf. on Machine Learning"},{"key":"ref30","article-title":"DreamGaussian4D: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0609-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref35","article-title":"DreamGaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3426953"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3584468"},{"key":"ref39","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Proc. of Advances in Neural Information Processing Systems"},{"key":"ref40","author":"Wu","year":"2015","journal-title":"Galileo: Perceiving physical object properties by integrating a physics engine with deep learning. Proc."},{"key":"ref41","first-page":"90689079","author":"Xia","year":"2018","journal-title":"Gibson env: Real-world perception for embodied agents. In Proc. of IEEE Conf. on Computer Vision and Pattern Recognition"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00420"},{"issue":"1","key":"ref43","article-title":"The dawn of 1 mms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160731"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356513"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_22"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref49","article-title":"CHASE: 3d-consistent human avatars with sparse inputs via gaussian splatting and contrastive learning","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"SG-GS: Photo-realistic animatable human avatars with semantically-guided gaussian splatting","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"HFGS: 4d gaussian splatting with emphasis on spatial and temporal high-frequency components for endoscopic scene reconstruction","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Smap: Self-supervised motion adaptation for physically plausible humanoid whole-body control","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Animate124: Animating one image to 4d dynamic scene","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_23"}],"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\/11445844.pdf?arnumber=11445844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:03Z","timestamp":1777611783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00498","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}