{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:53Z","timestamp":1766061653620,"version":"3.48.0"},"reference-count":76,"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/iros60139.2025.11246758","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"626-633","source":"Crossref","is-referenced-by-count":0,"title":["Adjacent-view Transformers for Supervised Surround-view Depth Estimation"],"prefix":"10.1109","author":[{"given":"Xianda","family":"Guo","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science"}]},{"given":"Wenjie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Waytous"}]},{"given":"Yunpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Tian","family":"Yang","sequence":"additional","affiliation":[{"name":"PhiGent Robotics"}]},{"given":"Chenming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics"}]},{"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"GigaAI"}]},{"given":"Qin","family":"Zou","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}]}],"member":"263","reference":[{"article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"NeurIPS","author":"Eigen","key":"ref1"},{"article-title":"Digging into self-supervised monocular depth prediction","volume-title":"ICCV","author":"Godard","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"article-title":"Openstereo: A comprehensive benchmark for stereo matching and strong baseline","year":"2023","author":"Guo","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","year":"2019","author":"Lee","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3150884"},{"article-title":"Surrounddepth: Entangling surrounding views for self-supervised multi-camera depth estimation","year":"2022","author":"Wei","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3416065"},{"article-title":"Va-depthnet: A variational approach to single image depth prediction","year":"2023","author":"Liu","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"article-title":"Depth anything v2","volume-title":"NeurIPS","author":"Yang","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2008.132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298660"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.97"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.49"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"article-title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","volume-title":"NeurIPS","author":"Bian","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00871"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01252"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00714"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00026"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3019967"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.56"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2007.1166"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00275"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.108"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00297"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00339"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00203"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197031"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.17"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_35"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00027"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00566"},{"article-title":"Hierarchical neural architecture search for deep stereo matching","volume-title":"NeurIPS","author":"Cheng","key":"ref63"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00298"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3193421"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01777"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548394"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246758.pdf?arnumber=11246758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:12Z","timestamp":1766061432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246758","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}