{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:28:50Z","timestamp":1780392530669,"version":"3.54.1"},"reference-count":68,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2127544,IIS-2433768"],"award-info":[{"award-number":["IIS-2127544,IIS-2433768"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00542","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5722-5733","source":"Crossref","is-referenced-by-count":4,"title":["DepR: Depth Guided Single-View Scene Reconstruction with Instance-Level Diffusion"],"prefix":"10.1109","author":[{"given":"Qingcheng","family":"Zhao","sequence":"first","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Xu","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwen","family":"Xie","sequence":"additional","affiliation":[{"name":"Lambda, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[{"name":"UC San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Bochkovskiy","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00478"},{"key":"ref6","first-page":"8282","article-title":"Panoptic 3d scene reconstruction from a single rgb image","volume-title":"In Advances in Neural Information Processing Systems","author":"Dahnert","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00062"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref11","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"In Advances in Neural Information Processing Systems","author":"Eigen","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3658236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00168"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"ref18","article-title":"Reparo: Compositional 3d assets generation with differentiable 3d layout alignment","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"LRM: Large reconstruction model for single image to 3d","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Hong","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.260"},{"key":"ref24","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01236"},{"key":"ref29","article-title":"Sparc: Sparse render-and-compare for cad model alignment in a single rgb image","author":"Langer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_25"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0976"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref35","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Liu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref38","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"In International Conference on Machine Learning","author":"Quinn Nichol","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"ref40","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref41","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Podell","year":"2024"},{"issue":"2","key":"ref42","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref48","article-title":"Denoising diffusion implicit models","volume-title":"In International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00314"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3974"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3873"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2070"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3658188"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01011"},{"key":"ref58","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687672"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618165"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1814"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00849"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3236"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1234"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"}],"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\/11444736.pdf?arnumber=11444736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:12Z","timestamp":1777611852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00542","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}