{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:13:25Z","timestamp":1784268805239,"version":"3.55.0"},"reference-count":88,"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\/iccv51701.2025.02580","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27794-27805","source":"Crossref","is-referenced-by-count":2,"title":["SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations"],"prefix":"10.1109","author":[{"given":"Songchun","family":"Zhang","sequence":"first","affiliation":[{"name":"ZJU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyao","family":"Xu","sequence":"additional","affiliation":[{"name":"ZJU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sitong","family":"Guo","sequence":"additional","affiliation":[{"name":"ZJU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongwei","family":"Xie","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"ZJU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"ZJU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changqing","family":"Zou","sequence":"additional","affiliation":[{"name":"ZJU"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02130"},{"key":"ref2","first-page":"19697","article-title":"Zip-nerf: Anti-aliased grid-based neural radiance fields","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Jonathan","year":"2023"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00567"},{"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":"10.1007\/978-3-031-72664-4_21"},{"key":"ref9","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00047"},{"key":"ref13","article-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds","author":"Fan","year":"2024","journal-title":"arXiv"},{"key":"ref14","article-title":"Scenescape: Text-driven consistent scene generation","volume":"36","author":"Fridman","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"ref18","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01246"},{"key":"ref21","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01909"},{"key":"ref23","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2024","journal-title":"ICLR"},{"key":"ref24","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01257"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref28","article-title":"Grounding image matching in 3d with mast3r","author":"Leroy","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00081"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00083"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"ref34","article-title":"Reconx: Reconstruct any scene from sparse views with video diffusion model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"9298","article-title":"Zero-1-to3: Zero-shot one image to 3d object","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Liu","year":"2023"},{"key":"ref36","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"You see it, you got it: Learning 3d creation on pose-free videos at scale","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"ref41","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref46","article-title":"Genwarp: Single image to novel views with semantic-preserving generative warping","author":"Seo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00086"},{"key":"ref49","first-page":"19313","article-title":"Light field networks: Neural scene representations with single-evaluation rendering","volume":"34","author":"Sitzmann","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","article-title":"Splatt3r: Zero-shot gaussian splatting from uncalibarated image pairs","author":"Smart","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_10"},{"key":"ref53","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00067"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_12"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01536"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00496"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref62","article-title":"Nerf-: Neural radiance fields without known camera parameters","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref63","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":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_7"},{"key":"ref67","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01534"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00798"},{"key":"ref72","article-title":"No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref74","article-title":"Nvs-solver: Video diffusion model as zero-shot novel view synthesizer","author":"You","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref78","article-title":"Cameras as rays: Pose estimation via ray diffusion","volume-title":"International Conference on Learning Representations (ICLR)","author":"Jason","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref82","first-page":"10170","article-title":"3dscenedreamer: Text-driven 3d-consistent scene generation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00537"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00928"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref88","article-title":"Fsgs: Real-time few-shot view synthesis using gaussian splatting","author":"Zhu","year":"2024","journal-title":"ECCV"}],"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\/11444810.pdf?arnumber=11444810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:25Z","timestamp":1777612045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02580","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}