{"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/noise-aware-unsupervised-deep-lidar-stereo","title":"Noise-Aware Unsupervised Deep Lidar-Stereo Fusion","arxiv_id":"1904.03868","date":"2019-04-08","proceeding":"CVPR 2019 6","authors":["Xuelian Cheng","Yiran Zhong","Yuchao Dao","Pan Ji","Hongdong Li"],"abstract":"In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo\nfusion network, which can be trained in an end-to-end manner without the need\nof ground truth depth maps. By introducing a novel \"Feedback Loop'' to connect\nthe network input with output, LidarStereoNet could tackle both noisy Lidar\npoints and misalignment between sensors that have been ignored in existing\nLidar-stereo fusion studies. Besides, we propose to incorporate a piecewise\nplanar model into network learning to further constrain depths to conform to\nthe underlying 3D geometry. Extensive quantitative and qualitative evaluations\non both real and synthetic datasets demonstrate the superiority of our method,\nwhich outperforms state-of-the-art stereo matching, depth completion and\nLidar-Stereo fusion approaches significantly.","url_abs":"http://arxiv.org/abs/1904.03868v1","url_pdf":"http://arxiv.org/pdf/1904.03868v1.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":"noise-aware-unsupervised-deep-lidar-stereo","repo_url":"https://github.com/XuelianCheng/LidarStereoNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"noise-aware-unsupervised-deep-lidar-stereo","repo_url":"https://github.com/AvrilCheng/LidarStereoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"noise-aware-unsupervised-deep-lidar-stereo","repo_url":"https://github.com/kairenye/LidarStereoFusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"depth-completion","task_name":"Depth Completion"},{"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=1904.03868","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}