{"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/self-supervised-learning-for-single-view","title":"Self-supervised Learning for Single View Depth and Surface Normal Estimation","arxiv_id":"1903.00112","date":"2019-03-01","proceeding":null,"authors":["Huangying Zhan","Chamara Saroj Weerasekera","Ravi Garg","Ian Reid"],"abstract":"In this work we present a self-supervised learning framework to\nsimultaneously train two Convolutional Neural Networks (CNNs) to predict depth\nand surface normals from a single image. In contrast to most existing\nframeworks which represent outdoor scenes as fronto-parallel planes at\npiece-wise smooth depth, we propose to predict depth with surface orientation\nwhile assuming that natural scenes have piece-wise smooth normals. We show that\na simple depth-normal consistency as a soft-constraint on the predictions is\nsufficient and effective for training both these networks simultaneously. The\ntrained normal network provides state-of-the-art predictions while the depth\nnetwork, relying on much realistic smooth normal assumption, outperforms the\ntraditional self-supervised depth prediction network by a large margin on the\nKITTI benchmark. Demo video: https://youtu.be/ZD-ZRsw7hdM","url_abs":"http://arxiv.org/abs/1903.00112v1","url_pdf":"http://arxiv.org/pdf/1903.00112v1.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":[],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"SelfDepthNorm","rank_in_archive_order":71,"of":79,"metrics":{"absolute relative error":"0.133"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.00112","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}