{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:27:45Z","timestamp":1768274865360,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 72192821, No. 62472282"],"award-info":[{"award-number":["No. 72192821, No. 62472282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Fundamental Research Funds for the Central Universities","award":["YG2023QNA35"],"award-info":[{"award-number":["YG2023QNA35"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1402135"],"award-info":[{"award-number":["25ZR1402135"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755159","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"1386-1394","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5488-8180","authenticated-orcid":false,"given":"Zhiwei","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9770-5938","authenticated-orcid":false,"given":"Ruikai","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5406-1011","authenticated-orcid":false,"given":"Weijian","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6905-4478","authenticated-orcid":false,"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-1196","authenticated-orcid":false,"given":"Xin","family":"Tan","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-0953","authenticated-orcid":false,"given":"Jingyu","family":"Gong","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China and Shanghai Key Laboratory of Computer Software Evaluating and Testing, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-7437","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Shariq Farooq Bhat Reiner Birkl Diana Wofk Peter Wonka and Matthias M\u00fcller. 2023. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. doi:10.48550\/ARXIV.2302.12288","DOI":"10.48550\/ARXIV.2302.12288"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01840"},{"key":"e_1_3_2_1_3_1","volume-title":"Single-image depth perception in the wild. Advances in neural information processing systems","author":"Chen Weifeng","year":"2016","unstructured":"Weifeng Chen, Zhao Fu, Dawei Yang, and Jia Deng. 2016. Single-image depth perception in the wild. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00966"},{"key":"e_1_3_2_1_6_1","volume-title":"Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems","author":"Eigen David","year":"2014","unstructured":"David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00026"},{"key":"e_1_3_2_1_9_1","volume-title":"Grin: Zero-shot metric depth with pixel-level diffusion. arXiv preprint arXiv:2409.09896","author":"Guizilini Vitor","year":"2024","unstructured":"Vitor Guizilini, Pavel Tokmakov, Achal Dave, and Rares Ambrus. 2024. Grin: Zero-shot metric depth with pixel-level diffusion. arXiv preprint arXiv:2409.09896 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150884"},{"key":"e_1_3_2_1_11_1","volume-title":"Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation","author":"Hu Mu","year":"2024","unstructured":"Mu Hu, Wei Yin, Chi Zhang, Zhipeng Cai, Xiaoxiao Long, Hao Chen, Kaixuan Wang, Gang Yu, Chunhua Shen, and Shaojie Shen. 2024. Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2006.153"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_15_1","first-page":"4032","article-title":"Self-supervised surround-view depth estimation with volumetric feature fusion","volume":"35","author":"Kim Jung-Hee","year":"2022","unstructured":"Jung-Hee Kim, Junhwa Hur, Tien Phuoc Nguyen, and Seong-Gyun Jeong. 2022. Self-supervised surround-view depth estimation with volumetric feature fusion. Advances in Neural Information Processing Systems, Vol. 35 (2022), 4032-4045.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062324"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00805"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00955"},{"key":"e_1_3_2_1_19_1","volume-title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation. arXiv preprint arXiv:2412.14015","author":"Lin Haotong","year":"2024","unstructured":"Haotong Lin, Sida Peng, Jingxiao Chen, Songyou Peng, Jiaming Sun, Minghuan Liu, Hujun Bao, Jiashi Feng, Xiaowei Zhou, and Bingyi Kang. 2024. Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation. arXiv preprint arXiv:2412.14015 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"BEVScope: Enhancing Self-Supervised Depth Estimation Leveraging Bird's-Eye-View in Dynamic Scenarios. arXiv preprint arXiv:2306.11598","author":"Mao Yucheng","year":"2023","unstructured":"Yucheng Mao, Ruowen Zhao, Tianbao Zhang, and Hang Zhao. 2023. BEVScope: Enhancing Self-Supervised Depth Estimation Leveraging Bird's-Eye-View in Dynamic Scenarios. arXiv preprint arXiv:2306.11598 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/robot.2007.364084"},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Min Zhiyuan","year":"2024","unstructured":"Zhiyuan Min, Yawei Luo, Jianwen Sun, and Yi Yang. 2024. Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/45ed1a72597594c097152ef9cc187762-Abstract-Conference.html"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3539627"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32793"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_14"},{"key":"e_1_3_2_1_27_1","volume-title":"Conference on robot learning. PMLR, 539-549","author":"Wei Yi","year":"2023","unstructured":"Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Yongming Rao, Guan Huang, Jiwen Lu, and Jie Zhou. 2023. Surrounddepth: Entangling surrounding views for self-supervised multi-camera depth estimation. In Conference on robot learning. PMLR, 539-549."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00069"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02062"},{"key":"e_1_3_2_1_31_1","unstructured":"Haofei Xu Songyou Peng Fangjinhua Wang Hermann Blum Daniel Barath Andreas Geiger and Marc Pollefeys. 2025. DepthSplat: Connecting Gaussian Splatting and Depth. In CVPR."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00744"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_2_1_34_1","first-page":"21875","article-title":"Depth anything v2","volume":"37","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024b. Depth anything v2. Advances in Neural Information Processing Systems, Vol. 37 (2024), 21875-21911.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00527"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612042"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:58:40Z","timestamp":1765310320000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":37,"alternative-id":["10.1145\/3746027.3755159","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755159","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}