{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:06Z","timestamp":1777889226286,"version":"3.51.4"},"reference-count":41,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12201497,62272375,12401674"],"award-info":[{"award-number":["12201497,62272375,12401674"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D5000240095"],"award-info":[{"award-number":["D5000240095"]}],"id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.00536","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5657-5666","source":"Crossref","is-referenced-by-count":0,"title":["Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Xie","sequence":"first","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armen","family":"Avetisyan","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henry","family":"Howard-Jenkins","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yawar","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Straub","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Newcombe","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasileios","family":"Balntas","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakob","family":"Engel","sequence":"additional","affiliation":[{"name":"Meta Reality Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cm3: A causal masked multimodal model of the internet","author":"Aghajanyan","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Santacoder: don\u2019t reach for the stars","author":"Allal","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_14"},{"key":"ref4","article-title":"Efficient training of language models to fill in the middle","author":"Bavarian","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Deepsvg: A hierarchical generative network for vector graphics animation","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Carlier","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_36"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"ref8","article-title":"Pix2seq: A language modeling framework for object detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref11","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dao","year":"2024"},{"key":"ref12","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Devlin","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.225"},{"key":"ref14","volume-title":"Blender: The freedom to create","year":"2023"},{"key":"ref15","article-title":"Incoder: A generative model for code infilling and synthesis","volume-title":"International Conference on Learning Representations (ICLR)","author":"Fried","year":"2023"},{"key":"ref16","article-title":"Computer-aided design as language","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ganin","year":"2021"},{"key":"ref17","article-title":"Convolutional sequence to sequence learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Gehring","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00104"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_18"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00604"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_34"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00266"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"ref25","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Polygen: An autoregressive generative model of 3d meshes","volume-title":"International Conference on Learning Representations (ICLR)","author":"Nash","year":"2020"},{"key":"ref27","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","article-title":"Code llama: Open foundation models for code","author":"Roziere","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Film: Fill-in language models for any-order generation","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref31","article-title":"Project aria: A new tool for egocentric multi-modal ai research","author":"Somasundaram","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Efm3d: A benchmark for measuring progress towards 3d egocentric foundation models","author":"Straub","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614303"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref35","article-title":"Neural discrete representation learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Van Den Oord","year":"2017"},{"key":"ref36","article-title":"Attention is all you need","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3283289.3283304"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00088"},{"key":"ref41","article-title":"The scene language: Representing scenes with programs, words, and embeddings","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11446027.pdf?arnumber=11446027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:06Z","timestamp":1777612146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00536","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}