{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:52:34Z","timestamp":1776113554330,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746058.3758405","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T14:35:03Z","timestamp":1758983703000},"page":"1-3","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["RealityCrafter: User-guided Editable 3D Scene Generation from a Single Image in Mixed Reality"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7336-5699","authenticated-orcid":false,"given":"Seokyoung","family":"Kim","sequence":"first","affiliation":[{"name":"Graduate School of Metaverse, KAIST, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6003-2181","authenticated-orcid":false,"given":"Dooyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"KI-ITC ARRC, KAIST, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6766-675X","authenticated-orcid":false,"given":"Taejun","family":"Son","sequence":"additional","affiliation":[{"name":"Graduate School of Metaverse, KAIST, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5501-4421","authenticated-orcid":false,"given":"Woontack","family":"Woo","sequence":"additional","affiliation":[{"name":"UVR Lab., KAIST, Daejeon, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2022. Whisper AI. https:\/\/github.com\/openai\/whisper OpenAI."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"e_1_3_3_1_4_2","first-page":"70","volume-title":"European Conference on Computer Vision","author":"Chen Zhekai","year":"2024","unstructured":"Zhekai Chen, Wen Wang, Zhen Yang, Zeqing Yuan, Hao Chen, and Chunhua Shen. 2024. FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior. In European Conference on Computer Vision. Springer, 70\u201387."},{"key":"e_1_3_3_1_5_2","unstructured":"Andreea Dogaru Mert \u00d6zer and Bernhard Egger. 2025. Gen3DSR: Generalizable 3d scene reconstruction via divide and conquer from a single view. International Conference on 3D Vision (2025)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672539.3686315"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01660"},{"key":"e_1_3_3_1_8_2","unstructured":"Weiyu Li Xuanyang Zhang Zheng Sun Di Qi Hao Li Wei Cheng Weiwei Cai Shihao Wu Jiarui Liu Zihao Wang et\u00a0al. 2025. Step1x-3d: Towards high-fidelity and controllable generation of textured 3d assets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.07747 (2025)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3644054"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Luigi Piccinelli Christos Sakaridis Yung-Hsu Yang Mattia Segu Siyuan Li Wim Abbeloos and Luc Van\u00a0Gool. 2025. Unidepthv2: Universal monocular metric depth estimation made simpler. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.20110 (2025).","DOI":"10.1109\/CVPR52734.2025.00104"},{"key":"e_1_3_3_1_11_2","unstructured":"Jiaxiang Tang Ruijie Lu Xiaokang Chen Xiang Wen Gang Zeng and Ziwei Liu. 2024. Intex: Interactive text-to-texture synthesis via unified depth-aware inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.11878 (2024)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714312"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00869"},{"key":"e_1_3_3_1_14_2","first-page":"419","volume-title":"European Conference on Computer Vision","author":"Yuan Haobo","year":"2024","unstructured":"Haobo Yuan, Xiangtai Li, Chong Zhou, Yining Li, Kai Chen, and Chen\u00a0Change Loy. 2024. Open-vocabulary SAM: Segment and recognize twenty-thousand classes interactively. In European Conference on Computer Vision. Springer, 419\u2013437."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676451"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST Adjunct '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Adjunct Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746058.3758405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T10:06:44Z","timestamp":1759745204000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746058.3758405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":14,"alternative-id":["10.1145\/3746058.3758405","10.1145\/3746058"],"URL":"https:\/\/doi.org\/10.1145\/3746058.3758405","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}