{"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/recurrent-neural-network-for-un-supervised","title":"Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth","arxiv_id":"1904.07087","date":"2019-04-15","proceeding":null,"authors":["Rui Wang","Stephen M. Pizer","Jan-Michael Frahm"],"abstract":"Deep learning-based, single-view depth estimation methods have recently shown\nhighly promising results. However, such methods ignore one of the most\nimportant features for determining depth in the human vision system, which is\nmotion. We propose a learning-based, multi-view dense depth map and odometry\nestimation method that uses Recurrent Neural Networks (RNN) and trains\nutilizing multi-view image reprojection and forward-backward flow-consistency\nlosses. Our model can be trained in a supervised or even unsupervised mode. It\nis designed for depth and visual odometry estimation from video where the input\nframes are temporally correlated. However, it also generalizes to single-view\ndepth estimation. Our method produces superior results to the state-of-the-art\napproaches for single-view and multi-view learning-based depth estimation on\nthe KITTI driving dataset.","url_abs":"http://arxiv.org/abs/1904.07087v1","url_pdf":"http://arxiv.org/pdf/1904.07087v1.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":"recurrent-neural-network-for-un-supervised","repo_url":"https://github.com/wrlife/RNN_depth_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"multi-view-learning","task_name":"MULTI-VIEW LEARNING"},{"task_slug":"visual-odometry","task_name":"Visual Odometry"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.07087","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}