{"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/single-view-stereo-matching","title":"Single View Stereo Matching","arxiv_id":"1803.02612","date":"2018-03-07","proceeding":"CVPR 2018 6","authors":["Yue Luo","Jimmy Ren","Mude Lin","Jiahao Pang","Wenxiu Sun","Hongsheng Li","Liang Lin"],"abstract":"Previous monocular depth estimation methods take a single view and directly\nregress the expected results. Though recent advances are made by applying\ngeometrically inspired loss functions during training, the inference procedure\ndoes not explicitly impose any geometrical constraint. Therefore these models\npurely rely on the quality of data and the effectiveness of learning to\ngeneralize. This either leads to suboptimal results or the demand of huge\namount of expensive ground truth labelled data to generate reasonable results.\nIn this paper, we show for the first time that the monocular depth estimation\nproblem can be reformulated as two sub-problems, a view synthesis procedure\nfollowed by stereo matching, with two intriguing properties, namely i)\ngeometrical constraints can be explicitly imposed during inference; ii) demand\non labelled depth data can be greatly alleviated. We show that the whole\npipeline can still be trained in an end-to-end fashion and this new formulation\nplays a critical role in advancing the performance. The resulting model\noutperforms all the previous monocular depth estimation methods as well as the\nstereo block matching method in the challenging KITTI dataset by only using a\nsmall number of real training data. The model also generalizes well to other\nmonocular depth estimation benchmarks. We also discuss the implications and the\nadvantages of solving monocular depth estimation using stereo methods.","url_abs":"http://arxiv.org/abs/1803.02612v2","url_pdf":"http://arxiv.org/pdf/1803.02612v2.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":"single-view-stereo-matching","repo_url":"https://github.com/lawy623/SVS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"stereo-matching","task_name":"Stereo Matching Hand"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"SVS","rank_in_archive_order":52,"of":79,"metrics":{"absolute relative error":"0.094"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.02612","atlas_url":"https://app.syntology.ai/?focus=1803.02612","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}