{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:05:44Z","timestamp":1784268344891,"version":"3.55.0"},"reference-count":97,"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\/iccv51701.2025.02304","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24846-24857","source":"Crossref","is-referenced-by-count":7,"title":["Bolt3D: Generating 3D Scenes in Seconds"],"prefix":"10.1109","author":[{"given":"Stanislaw","family":"Szymanowicz","sequence":"first","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason Y.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pratul","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arthur","family":"Brussee","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksander","family":"Holynski","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricardo","family":"Martin-Brualla","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan T.","family":"Barron","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Henzler","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"ref2","article-title":"Denoising diffusion via image-based rendering","author":"Anciukevi\u010dius","year":"2024","journal-title":"ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref4","article-title":"Gaudi: A neural architect for immersive 3d scene generation","author":"Bautista","year":"2022","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref10","article-title":"MVS-plat360: Feed-forward 360 Scene Synthesis from Sparse Views","volume-title":"NeurIPS","author":"Chen","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref12","article-title":"Auto-encoding variational bayes","author":"Welling","year":"2014","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"ref14","article-title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00988"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00030"},{"key":"ref17","article-title":"NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-Aware Diffusion","volume-title":"ICML","author":"Gu","year":"2023"},{"key":"ref18","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2025","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01008"},{"key":"ref20","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2018","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00482"},{"key":"ref23","article-title":"LRM: Large Reconstruction Model for Single Image to 3D","author":"Hong","year":"2024","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref25","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Learning 3d-aware latent diffusion models in view space","author":"Schwarz","year":"2024","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01235"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00083"},{"key":"ref32","article-title":"DiffSplat: Repurposing Image Diffusion Models for Scalable 3D Gaussian Splat Generation","author":"Lin","year":"2025","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref34","article-title":"Reconx: Reconstruct any scene from sparse views with video diffusion model","author":"Liu","year":"2024","journal-title":"arXiv:2408.16767"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref36","article-title":"SyncDreamer: Learning to Generate Multiview-consistent Images from a Single-view Image","author":"Liu","year":"2024","journal-title":"ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00194"},{"key":"ref38","article-title":"IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation","author":"Melas-Kyriazi","year":"2024","journal-title":"ICML"},{"key":"ref39","article-title":"Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation","author":"Meng","year":"2024","journal-title":"arXiv preprint arXiv:"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref47","article-title":"Scube: Instant large-scale scene reconstruction using voxsplats","author":"Ren","year":"2024","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687699"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"ref51","article-title":"Progressive Distillation for Fast Sampling of Diffusion Models","author":"Salimans","year":"2022","journal-title":"ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref53","article-title":"Graf: Generative radiance fields for 3d-aware image synthesis","volume-title":"NeurIPS","author":"Schwarz","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02554"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"ref56","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv:2308.16512"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"ref58","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref59","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2025","journal-title":"ICCV"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00814"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00067"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.230"},{"key":"ref65","article-title":"Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision","author":"Tewari","year":"2023","journal-title":"NeurIPS"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.30"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_19"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref69","article-title":"From an Image to a Scene: Learning to Imagine the World from a Million 360\u00b0 Videos","author":"Wallingford","year":"2025","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01993-0"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref73","article-title":"Novel View Synthesis with Diffusion Models","volume-title":"ICLR","author":"Watson","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_27"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00875"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01534"},{"key":"ref79","article-title":"DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model","author":"Xu","year":"2024","journal-title":"ICLR"},{"key":"ref80","article-title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","author":"Ye","year":"2025","journal-title":"ICLR"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref86","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","author":"Yu","year":"2021","journal-title":"CVPR"},{"key":"ref87","article-title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","volume-title":"arXiv:2409.02048","author":"Yu","year":"2024"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00272"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01153"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01211"}],"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\/11448985.pdf?arnumber=11448985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:10Z","timestamp":1777529890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11448985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02304","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}