{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:19:37Z","timestamp":1781007577578,"version":"3.54.1"},"reference-count":55,"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\/iccv51701.2025.00588","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6231-6241","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Inexact CAD Model Alignment from a Single Image"],"prefix":"10.1109","author":[{"given":"Pattaramanee","family":"Arsomngern","sequence":"first","affiliation":[{"name":"VISTEC,Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sasikarn","family":"Khwanmuang","sequence":"additional","affiliation":[{"name":"VISTEC,Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Supasorn","family":"Suwajanakorn","sequence":"additional","affiliation":[{"name":"VISTEC,Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611464"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00272"},{"key":"ref3","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Bochkovskiy","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"ArXiv"},{"key":"ref8","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01711"},{"key":"ref10","first-page":"1","article-title":"Indoor semantic segmentation using depth information","volume-title":"First International Conference on Learning Representations (ICLR 2013)","author":"Couprie","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01263"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3658236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1217599"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00962"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01236"},{"key":"ref25","first-page":"715","article-title":"Megapose: 6d pose estimation of novel objects via render and compare","volume-title":"Proceedings of The 6th Conference on Robot Learning","author":"Labb\u00e9","year":"2023"},{"key":"ref26","article-title":"Sparc: Sparse render-and-compare for cad model alignment in a single rgb image","volume-title":"Proc. British Machine Vision Conference, London","author":"Langer","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00997"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02646-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"ref30","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"ArXiv"},{"key":"ref31","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2017"},{"key":"ref32","article-title":"Generating images with 3d annotations using diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ma","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3146082"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01846"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"ref36","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_10"},{"key":"ref38","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref40","article-title":"Accelerating 3d deep learning with pytorch3d","author":"Ravi","journal-title":"arXiv preprint"},{"key":"ref41","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3118833"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/34.6778"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref51","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"}],"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\/11443613.pdf?arnumber=11443613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:45:06Z","timestamp":1777610706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00588","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}