{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:28:10Z","timestamp":1784399290727,"version":"3.55.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00348","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3567-3577","source":"Crossref","is-referenced-by-count":1,"title":["Comp4D: Compositional 4D Scene Generation"],"prefix":"10.1109","author":[{"given":"Hanwen","family":"Liang","sequence":"first","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dejia","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Texas,Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neel P.","family":"Bhatt","sequence":"additional","affiliation":[{"name":"University of Texas,Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hezhen","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Texas,Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxue","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos N.","family":"Plataniotis","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Zeroscope","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_4"},{"key":"ref4","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161068"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657463"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"ref10","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning","author":"Ichter"},{"key":"ref11","article-title":"Consistent4d: Consistent 360 {\\deg} dynamic object generation from monocular video","author":"Jiang","year":"2023"},{"key":"ref12","article-title":"An efficient 3d gaussian representation for monocular\/multi-view dynamic scenes","author":"Katsumata","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3410155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1987"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref17","article-title":"A comprehensive evaluation of gpt-4v on knowledge-intensive visual question answering","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00813"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01997"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00819"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.641"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref25","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref26","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022"},{"key":"ref27","article-title":"Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1487"},{"key":"ref29","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref30","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref34","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023"},{"key":"ref35","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023"},{"key":"ref36","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023"},{"key":"ref37","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace10090770"},{"key":"ref39","article-title":"Cg3d: Compositional generation for text-to-3d via gaussian splatting","author":"Vilesov","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref42","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2023"},{"key":"ref43","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","article-title":"4d gaussian splatting for real-time dynamic scene rendering","author":"Wu","year":"2023"},{"key":"ref45","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","author":"Wu","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754704"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00435"},{"key":"ref49","article-title":"Fine-tuning language models using formal methods feedback","author":"Yang","year":"2023"},{"issue":"1","key":"ref50","first-page":"1","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023"},{"key":"ref51","article-title":"Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting","author":"Yang","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref53","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0488"},{"key":"ref55","article-title":"Animate124: Animating one image to 4d dynamic scene","author":"Zhao","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00697"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492730.pdf?arnumber=11492730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:59:56Z","timestamp":1778047196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00348","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}