{"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/learning-monocular-depth-by-distilling-cross","title":"Learning Monocular Depth by Distilling Cross-domain Stereo Networks","arxiv_id":"1808.06586","date":"2018-08-20","proceeding":"ECCV 2018 9","authors":["Xiaoyang Guo","Hongsheng Li","Shuai Yi","Jimmy Ren","Xiaogang Wang"],"abstract":"Monocular depth estimation aims at estimating a pixelwise depth map for a\nsingle image, which has wide applications in scene understanding and autonomous\ndriving. Existing supervised and unsupervised methods face great challenges.\nSupervised methods require large amounts of depth measurement data, which are\ngenerally difficult to obtain, while unsupervised methods are usually limited\nin estimation accuracy. Synthetic data generated by graphics engines provide a\npossible solution for collecting large amounts of depth data. However, the\nlarge domain gaps between synthetic and realistic data make directly training\nwith them challenging. In this paper, we propose to use the stereo matching\nnetwork as a proxy to learn depth from synthetic data and use predicted stereo\ndisparity maps for supervising the monocular depth estimation network.\nCross-domain synthetic data could be fully utilized in this novel framework.\nDifferent strategies are proposed to ensure learned depth perception capability\nwell transferred across different domains. Our extensive experiments show\nstate-of-the-art results of monocular depth estimation on KITTI dataset.","url_abs":"http://arxiv.org/abs/1808.06586v1","url_pdf":"http://arxiv.org/pdf/1808.06586v1.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":"learning-monocular-depth-by-distilling-cross","repo_url":"https://github.com/xy-guo/Learning-Monocular-Depth-by-Stereo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"stereo-matching","task_name":"Stereo Matching Hand"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.06586","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}