{"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/learn-stereo-infer-mono-siamese-networks-for","title":"Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation","arxiv_id":"1905.00401","date":"2019-05-01","proceeding":null,"authors":["Matan Goldman","Tal Hassner","Shai Avidan"],"abstract":"The field of self-supervised monocular depth estimation has seen huge\nadvancements in recent years. Most methods assume stereo data is available\nduring training but usually under-utilize it and only treat it as a reference\nsignal. We propose a novel self-supervised approach which uses both left and\nright images equally during training, but can still be used with a single input\nimage at test time, for monocular depth estimation. Our Siamese network\narchitecture consists of two, twin networks, each learns to predict a disparity\nmap from a single image. At test time, however, only one of these networks is\nused in order to infer depth. We show state-of-the-art results on the standard\nKITTI Eigen split benchmark as well as being the highest scoring\nself-supervised method on the new KITTI single view benchmark. To demonstrate\nthe ability of our method to generalize to new data sets, we further provide\nresults on the Make3D benchmark, which was not used during training.","url_abs":"http://arxiv.org/abs/1905.00401v1","url_pdf":"http://arxiv.org/pdf/1905.00401v1.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":"learn-stereo-infer-mono-siamese-networks-for","repo_url":"https://github.com/mtngld/lsim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"LSIM","rank_in_archive_order":64,"of":79,"metrics":{"absolute relative error":"0.113"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}