{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:00:05Z","timestamp":1791478805141,"version":"4.3.4"},"reference-count":84,"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\/iccv51701.2025.02554","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27510-27520","source":"Crossref","is-referenced-by-count":5,"title":["Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors"],"prefix":"10.1109","author":[{"given":"Katja","family":"Schwarz","sequence":"first","affiliation":[{"name":"Meta Reality Labs Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Norman","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Kontschieder","sequence":"additional","affiliation":[{"name":"Meta Reality Labs Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Denoising diffusion via image-based rendering","author":"Anciukevicius","year":"2024","journal-title":"ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1820"},{"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\/iccv51070.2023.00389"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref9","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref12","author":"Fan","year":"2024","journal-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds"},{"key":"ref13","author":"Gao","year":"2024","journal-title":"Barron, and Ben Poole. CAT3D: create anything in 3d with multi-view diffusion models"},{"key":"ref14","author":"He","year":"2024","journal-title":"Cameractrl: Enabling camera control for text-to-video generation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2004.1315232"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00467"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref19","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"key":"ref20","article-title":"Cascaded diffusion models for high fidelity image generation","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","article-title":"LRM: large reconstruction model for single image to 3d","author":"Hong","year":"2024","journal-title":"ICLR"},{"key":"ref22","volume-title":"Lvsm: A large view synthesis model with minimal 3d inductive bias","author":"Jin","year":"2024"},{"key":"ref23","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00083"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref31","author":"Loshchilov","year":"2017","journal-title":"Fixing weight decay regularization in adam"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref35","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"ref39","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"CoRR","author":"Podell","year":"2023"},{"key":"ref40","author":"Poole","year":"2022","journal-title":"Barron, and Ben Mildenhall. Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref41","article-title":"Scube: Instant large-scale scene reconstruction using voxsplats","author":"Ren","year":"2024","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"ref45","author":"Salimans","year":"2022","journal-title":"Progressive distillation for fast sampling of diffusion models"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00900"},{"key":"ref47","article-title":"Graf: Generative radiance fields for 3d-aware image synthesis","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Schwarz","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2464"},{"key":"ref49","article-title":"Wildfusion: Learning 3d-aware latent diffusion models in view space","author":"Schwarz","year":"2024","journal-title":"ICLR"},{"key":"ref50","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2024","journal-title":"ICLR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00086"},{"key":"ref52","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref53","author":"Sitzmann","year":"2019","journal-title":"Scene representation networks: Continuous 3d-structure-aware neural scene representations"},{"key":"ref54","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref55","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref56","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref57","author":"Sun","year":"2024","journal-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"ref60","article-title":"Freeman, and Vincent Sitzmann. Diffusion with forward models: Solving stochastic inverse problems without direct supervision","author":"Tewari","year":"2023","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01490"},{"key":"ref62","author":"Unterthiner","year":"2018","journal-title":"Towards accurate generative models of video: A new metric & challenges"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref67","article-title":"Novel view synthesis with diffusion models","volume-title":"ICLR","author":"Watson","year":"2023"},{"key":"ref68","author":"Watson","year":"2024","journal-title":"Controlling space and time with diffusion models"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_27"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02036"},{"key":"ref71","author":"Xu","year":"2024","journal-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.13169\/prometheus.39.3.0143"},{"key":"ref78","article-title":"LION: latent point diffusion models for 3d shape generation","author":"Zeng","year":"2022","journal-title":"NeurIPS"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01211"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_9"}],"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\/11444789.pdf?arnumber=11444789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:19Z","timestamp":1777613419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02554","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}