{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:04Z","timestamp":1765008844131,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3771023","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Fine-Scale Change Detection Using 3D Gaussian Splatting and VLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7412-7426","authenticated-orcid":false,"given":"Satoshi","family":"Date","sequence":"first","affiliation":[{"name":"Mitsui Sumitomo Insurance Co., Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3387-2816","authenticated-orcid":false,"given":"Shojiro","family":"Tsutsui","sequence":"additional","affiliation":[{"name":"Mitsui Sumitomo Insurance Co., Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6819-4305","authenticated-orcid":false,"given":"Israel","family":"Mendon\u00e7a","sequence":"additional","affiliation":[{"name":"Kumamoto University, Kumamoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0861-849X","authenticated-orcid":false,"given":"Masayoshi","family":"Aritsugi","sequence":"additional","affiliation":[{"name":"Kumamoto University, Kumamoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Paul\u00a0J Besl and Neil\u00a0D McKay. 1992. Method for registration of 3-D shapes. Proceedings of SPIE - The International Society for Optical Engineering Sensor Fusion IV: Control Paradigms and Data Structures 1611 (1992) 586\u2013606. 10.1117\/12.57955","DOI":"10.1117\/12.57955"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Jiazhong Cen Jiemin Fang Chen Yang Lingxi Xie Xiaopeng Zhang Wei Shen and Qi Tian. 2025. Segment Any 3D Gaussians. Proceedings of the AAAI Conference on Artificial Intelligence 39 2 (Apr. 2025) 1971\u20131979. 10.1609\/aaai.v39i2.32193","DOI":"10.1609\/aaai.v39i2.32193"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Anurag Dalal Daniel Hagen Kjell\u00a0G. Robbersmyr and Kristian\u00a0Muri Knausg\u00e5rd. 2024. Gaussian Splatting: 3D Reconstruction and Novel View Synthesis: A Review. IEEE Access 12 (2024) 96797\u201396820. 10.1109\/ACCESS.2024.3408318","DOI":"10.1109\/ACCESS.2024.3408318"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIxMM62960.2025.00013"},{"key":"e_1_3_3_1_6_2","unstructured":"Zhiwen Fan Jian Zhang Renjie Li Junge Zhang Runjin Chen Hezhen Hu Kevin Wang Huaizhi Qu Dilin Wang Zhicheng Yan Hongyu Xu Justin Theiss Tianlong Chen Jiachen Li Zhengzhong Tu Zhangyang Wang and Rakesh Ranjan. 2025. VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction. arxiv:https:\/\/arXiv.org\/abs\/2505.20279\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2505.20279"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Martin\u00a0A. Fischler and Robert\u00a0C. Bolles. 1981. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24 6 (June 1981) 381\u2013395. 10.1145\/358669.358692","DOI":"10.1145\/358669.358692"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics 42 4 (July 2023) 137:1\u2013137:14. https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_1_9_2","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. arxiv:https:\/\/arXiv.org\/abs\/2304.02643\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2304.02643"},{"key":"e_1_3_3_1_10_2","unstructured":"Han-Hung Lee Manolis Savva and Angel\u00a0X. Chang. 2024. Text-to-3D Shape Generation. arxiv:https:\/\/arXiv.org\/abs\/2403.13289\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2403.13289"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/3666122.3667638"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Ziqi Lu Jianbo Ye and John Leonard. 2025. 3DGS-CD: 3D Gaussian Splatting-Based Change Detection for Physical Object Rearrangement. IEEE Robotics and Automation Letters 10 3 (2025) 2662\u20132669. 10.1109\/LRA.2025.3533457","DOI":"10.1109\/LRA.2025.3533457"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/UR61395.2024.10597504"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Ben Mildenhall Pratul\u00a0P. Srinivasan Matthew Tancik Jonathan\u00a0T. Barron Ravi Ramamoorthi and Ren Ng. 2021. NeRF: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (Dec. 2021) 99\u2013106. 10.1145\/3503250","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-942"},{"key":"e_1_3_3_1_16_2","unstructured":"Wentao Mo and Yang Liu. 2024. Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA. arxiv:https:\/\/arXiv.org\/abs\/2402.15933\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2402.15933"},{"key":"e_1_3_3_1_17_2","unstructured":"OpenAI. 2024. GPT-4o Technical Report. https:\/\/openai.com\/research\/gpt-4o. Accessed: 2025-07-16."},{"key":"e_1_3_3_1_18_2","volume-title":"open Multi-View Stereo reconstruction library","year":"2024","unstructured":"OpenMVS. 2024. open Multi-View Stereo reconstruction library. http:\/\/cdcseacave.github.io\/ Accessed: 2025-07-26."},{"key":"e_1_3_3_1_19_2","unstructured":"Puyuan Peng Shang-Wen Li Okko R\u00e4s\u00e4nen Abdelrahman Mohamed and David Harwath. 2023. Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded Self-Supervised Speech Model. arxiv:https:\/\/arXiv.org\/abs\/2305.11435\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2305.11435"},{"key":"e_1_3_3_1_20_2","unstructured":"Zhiliang Peng Wenhui Wang Li Dong Yaru Hao Shaohan Huang Shuming Ma and Furu Wei. 2023. Kosmos-2: Grounding Multimodal Large Language Models to the World. arxiv:https:\/\/arXiv.org\/abs\/2306.14824\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2306.14824"},{"key":"e_1_3_3_1_21_2","series-title":"Proceedings of Machine Learning Research","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, USA, 8748\u20138763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"e_1_3_3_1_23_2","volume-title":"COLMAP - Structure-from-Motion and Multi-View Stereo","author":"Schoenberger Johannes\u00a0L.","year":"2025","unstructured":"Johannes\u00a0L. Schoenberger. 2025. COLMAP - Structure-from-Motion and Multi-View Stereo. https:\/\/colmap.github.io\/ Accessed: 2025-07-26."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-931"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Tong Wu Yu-Jie Yuan Ling-Xiao Zhang Jie Yang Yan-Pei Cao Ling-Qi Yan and Lin Gao. 2024. Recent advances in 3D Gaussian splatting. Computational Visual Media 10 4 (2024) 613\u2013642. 10.1007\/s41095-024-0436-y","DOI":"10.1007\/s41095-024-0436-y"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677389.3702516"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3771023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:09:42Z","timestamp":1765008582000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3771023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":28,"alternative-id":["10.1145\/3743093.3771023","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3771023","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}