{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:57:04Z","timestamp":1780527424744,"version":"3.54.1"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00058","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"543-553","source":"Crossref","is-referenced-by-count":1,"title":["SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass"],"prefix":"10.1109","author":[{"given":"Yanxu","family":"Meng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoning","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00856"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00478"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref7","article-title":"Vision transformers need registers","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Darcet","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755132"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3658236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00275"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_26"},{"key":"ref21","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Conference on Neural Information Processing Systems","author":"Heusel","year":"2017"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","volume-title":"Conference on Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02202"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01520"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555394"},{"key":"ref26","article-title":"Hunyuan3d 2.1: From images to highfidelity 3d assets with production-ready pbr material","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01921"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref29","article-title":"Auto-encoding variational bayes","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kingma","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref31","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Li","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref34","article-title":"Partcrafter: Structured 3d mesh generation via compositional latent diffusion transformers","volume-title":"Conference on Neural Information Processing Systems","author":"Lin","year":"2025"},{"key":"ref35","article-title":"Scenethesis: A language and vision agentic framework for 3d scene generation","author":"Ling","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Flow matching for generative modeling","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Lipman","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"ref38","article-title":"Agentic 3d scene generation with spatially contextualized vlms","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"ref42","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref45","article-title":"Sam 2: Segment anything in images and videos","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Ravi","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"ref49","article-title":"Towards geometric and textural consistency 3d scene generation via single image-guided model generation and layout optimization","author":"Tang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Aether: Geometric-aware unified world modeling","volume-title":"Proceedings of the International Conference on Computer Vision","author":"Team","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00388"},{"key":"ref56","article-title":"Mrgen: Diffusion-based controllable data engine for mri segmentation towards unannotated modalities","volume-title":"Proceedings of the International Conference on Computer Vision","author":"Wu","year":"2025"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref59","article-title":"Dmv3d: Denoising multi-view diffusion using 3d large reconstruction model","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Xu","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3730841"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00163"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1307"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3091"},{"key":"ref67","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00542"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533217.pdf?arnumber=11533217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:01:45Z","timestamp":1779944505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00058","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}