{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:08Z","timestamp":1781538848467,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810646","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1064-1072","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PanoAdapter: Efficient Adaptation of Depth Foundation Models for Immersive Multimedia via Spherical Rectification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9212-3122","authenticated-orcid":false,"given":"Wei","family":"Xue","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing city, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7192-2593","authenticated-orcid":false,"given":"Zhiyong","family":"Huo","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing city, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01275"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00947"},{"key":"e_1_3_3_1_4_2","unstructured":"Iro Armeni Sasha Sax Amir\u00a0R. Zamir and Silvio Savarese. 2017. Joint 2D-3D-Semantic Data for Indoor Scene Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1702.01105 (2017). arxiv:https:\/\/arXiv.org\/abs\/1702.01105"},{"key":"e_1_3_3_1_5_2","unstructured":"Aleksei Bochkovskii Ama\u00ebl Delaunoy Hugo Germain Marcel Santos Yichao Zhou Stephan\u00a0R. Richter and Vladlen Koltun. 2024. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.02073 (2024). arxiv:https:\/\/arXiv.org\/abs\/2410.02073"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Jill\u00a0M. Boyce Renaud Dor\u00e9 Adrian Dziembowski Julien Fleureau Joel Jung Bart Kroon Basel Salahieh Vinod Kumar\u00a0Malamal Vadakital and Lu Yu. 2021. MPEG Immersive Video Coding Standard. Proc. IEEE 109 9 (2021) 1521\u20131536.","DOI":"10.1109\/JPROC.2021.3062590"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00100"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Angel Chang Angela Dai Thomas Funkhouser Maciej Halber Matthias Niessner Manolis Savva Shuran Song Andy Zeng and Yinda Zhang. 2017. Matterport3D: Learning from RGB-D Data in Indoor Environments. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1709.06158 (2017). arxiv:https:\/\/arXiv.org\/abs\/1709.06158","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01833"},{"key":"e_1_3_3_1_10_2","unstructured":"Zhe Chen Yuchen Duan Wenhai Wang Junjun He Tong Lu Jifeng Dai and Yu Qiao. 2022. Vision Transformer Adapter for Dense Predictions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.08534 (2022). arxiv:https:\/\/arXiv.org\/abs\/2205.08534"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32239"},{"key":"e_1_3_3_1_12_2","unstructured":"Alexey Dosovitskiy. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020). arxiv:https:\/\/arXiv.org\/abs\/2010.11929"},{"key":"e_1_3_3_1_13_2","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 (NeurIPS) 27 (2014)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02514"},{"key":"e_1_3_3_1_16_2","unstructured":"Edward\u00a0J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. LoRA: Low-rank Adaptation of Large Language Models. Proceedings of the International Conference on Learning Representations (ICLR) 1 2 (2022) 3."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Hualie Jiang Zhe Sheng Siyu Zhu Zilong Dong and Rui Huang. 2021. Unifuse: Unidirectional Fusion for 360 Panorama Depth Estimation. IEEE Robotics and Automation Letters 6 2 (2021) 1519\u20131526.","DOI":"10.1109\/LRA.2021.3058957"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_1_19_2","unstructured":"Haodong Li Wangguangdong Zheng Jing He Yuhao Liu Xin Lin Xin Yang Ying-Cong Chen and Chunchao Guo. 2025. DA2: Depth Anything in Any Direction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.26618 (2025). arxiv:https:\/\/arXiv.org\/abs\/2509.26618"},{"key":"e_1_3_3_1_20_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Li Ming","year":"2022","unstructured":"Ming Li, Xueqian Jin, Xuejiao Hu, Jingzhao Dai, Sidan Du, and Yang Li. 2022. MODE: Multi-view Omnidirectional Depth Estimation with 360\u00b0 Cameras. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00074"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"e_1_3_3_1_23_2","unstructured":"Xin Lin Meixi Song Dizhe Zhang Wenxuan Lu Haodong Li Bo Du Ming-Hsuan Yang Truong Nguyen and Lu Qi. 2025. Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.16913 (2025). arxiv:https:\/\/arXiv.org\/abs\/2512.16913"},{"key":"e_1_3_3_1_24_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017). arxiv:https:\/\/arXiv.org\/abs\/1711.05101"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Kevin Matzen Michael\u00a0F. Cohen Bryce Evans Johannes Kopf and Richard Szeliski. 2017. Low-cost 360 Stereo Photography and Video Capture. ACM Transactions on Graphics (TOG) 36 4 (2017) 1\u201312.","DOI":"10.1145\/3072959.3073645"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","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 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_1_27_2","unstructured":"Adam Paszke et\u00a0al. 2019. PyTorch: An Imperative Style High-performance Deep Learning Library. Advances in Neural Information Processing Systems (NeurIPS) 32 (2019)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Ren\u00e9 Ranftl Katrin Lasinger David Hafner Konrad Schindler and Vladlen Koltun. 2020. Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 44 3 (2020) 1623\u20131637.","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"e_1_3_3_1_31_2","unstructured":"Zhijie Shen Chunyu Lin Kang Liao Lang Nie Zishuo Zheng and Yao Zhao. 2022. Panoformer: Panorama Transformer for Indoor 360\u00b0 Depth Estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.09283 7 (2022). arxiv:https:\/\/arXiv.org\/abs\/2203.09283"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00260"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00054"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Fu-En Wang Yu-Hsuan Yeh Yi-Hsuan Tsai Wei-Chen Chiu and Min Sun. 2022. Bifuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 45 5 (2022) 5448\u20135460.","DOI":"10.1109\/TPAMI.2022.3203516"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Ning-Hsu\u00a0Albert Wang and Yu-Lun Liu. 2024. Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024) 127739\u2013127764.","DOI":"10.52202\/079017-4056"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"e_1_3_3_1_37_2","unstructured":"Lihe Yang Bingyi Kang Zilong Huang Zhen Zhao Xiaogang Xu Jiashi Feng and Hengshuang Zhao. 2024. Depth Anything V2. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09414 (2024). arxiv:https:\/\/arXiv.org\/abs\/2406.09414"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00561"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_28"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:58:41Z","timestamp":1781535521000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":40,"alternative-id":["10.1145\/3805622.3810646","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810646","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}