{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:18:29Z","timestamp":1782317909233,"version":"3.54.5"},"reference-count":69,"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\/iccv51701.2025.02353","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25367-25377","source":"Crossref","is-referenced-by-count":4,"title":["REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment"],"prefix":"10.1109","author":[{"given":"Haonan","family":"Han","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Liao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiankai","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunnan","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Zha","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanhua","family":"Li","sequence":"additional","affiliation":[{"name":"Harvard University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref5","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"Cuturi","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01263"},{"key":"ref7","article-title":"Objaverse-xl: A universe of 10 ~{m}+3 ~{d} objects","author":"Deitke","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015775"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref13","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref14","first-page":"2023","article-title":"Stable Diffusion Infinity","year":"2023","journal-title":"Stable diffusion infinity"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"ref20","article-title":"Generative ai meets 3d: A survey on text-to-3d in aigc era","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02097-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02049"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00107"},{"key":"ref25","article-title":"Advances in 3d generation: A survey","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680994"},{"key":"ref28","article-title":"Towards language-guided interactive 3d generation: Llms as layout interpreter with generative feedback","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00960"},{"key":"ref30","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref32","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00951"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"ref38","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00026"},{"key":"ref40","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Poole","year":"2023"},{"key":"ref42","article-title":"Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref46","volume-title":"Let 2d diffusion model know 3dconsistency for robust text-to-3d generation","author":"Seo"},{"key":"ref47","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Toss: High-quality text-guided novel view synthesis from a single image","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517719"},{"key":"ref51","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00434"},{"key":"ref54","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","article-title":"Cg3d: Compositional generation for text-to-3d via gaussian splatting","author":"Vilesov","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01214"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92387-6_22"},{"key":"ref60","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref61","article-title":"Consistent123: Improve consistency for one image to 3d object synthesis","author":"Weng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555479"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687672"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref67","article-title":"Dreamscape: 3d scene creation via gaussian splatting joint correlation modeling","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_18"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/11445265.pdf?arnumber=11445265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:24Z","timestamp":1777529664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02353","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}