{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/digging-into-self-supervised-monocular-depth-1","title":"Digging Into Self-Supervised Monocular Depth Estimation","arxiv_id":null,"date":"2019-10-01","proceeding":"ICCV 2019 10","authors":["Clement Godard"," Oisin Mac Aodha"," Michael Firman"," Gabriel J. Brostow"],"abstract":"Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark. \r","url_abs":"http://openaccess.thecvf.com/content_ICCV_2019/html/Godard_Digging_Into_Self-Supervised_Monocular_Depth_Estimation_ICCV_2019_paper.html","url_pdf":"http://openaccess.thecvf.com/content_ICCV_2019/papers/Godard_Digging_Into_Self-Supervised_Monocular_Depth_Estimation_ICCV_2019_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"digging-into-self-supervised-monocular-depth-1","repo_url":"https://github.com/nianticlabs/monodepth2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"digging-into-self-supervised-monocular-depth-1","repo_url":"https://github.com/IcarusWizard/monodepth2-paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"digging-into-self-supervised-monocular-depth-1","repo_url":"https://github.com/bolianchen/monodepth2_on_nuscenes_cityscapes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"Monodepth2 MS","rank_in_archive_order":41,"of":55,"metrics":{"absolute relative error":"0.106"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"Monodepth2 S","rank_in_archive_order":46,"of":55,"metrics":{"absolute relative error":"0.109"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"Monodepth2 M","rank_in_archive_order":53,"of":55,"metrics":{"Test frames":"1","absolute relative error":"0.115"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}