{"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/unsupervised-scale-consistent-depth-learning","title":"Unsupervised Scale-consistent Depth Learning from Video","arxiv_id":"2105.11610","date":"2021-05-25","proceeding":null,"authors":["Jia-Wang Bian","Huangying Zhan","Naiyan Wang","Zhichao Li","Le Zhang","Chunhua Shen","Ming-Ming Cheng","Ian Reid"],"abstract":"We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions include: (i) we propose a geometry consistency loss, which penalizes the inconsistency of predicted depths between adjacent views; (ii) we propose a self-discovered mask to automatically localize moving objects that violate the underlying static scene assumption and cause noisy signals during training; (iii) we demonstrate the efficacy of each component with a detailed ablation study and show high-quality depth estimation results in both KITTI and NYUv2 datasets. Moreover, thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system for more robust and accurate tracking. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training. Finally, we provide several demos for qualitative evaluation.","url_abs":"https://arxiv.org/abs/2105.11610v1","url_pdf":"https://arxiv.org/pdf/2105.11610v1.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":"unsupervised-scale-consistent-depth-learning","repo_url":"https://github.com/JiawangBian/sc_depth_pl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"unsupervised-scale-consistent-depth-learning","repo_url":"https://github.com/JiawangBian/SC-SfMLearner-Release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"monocular-visual-odometry","task_name":"Monocular Visual Odometry"},{"task_slug":"simultaneous-localization-and-mapping","task_name":"Simultaneous Localization and Mapping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"SC-Depth (ResNet 50)","rank_in_archive_order":65,"of":79,"metrics":{"Delta < 1.25":"0.873","Delta < 1.25^2":"0.960","Delta < 1.25^3":"0.982","RMSE":"4.706","RMSE log":"0.191","absolute relative error":"0.114"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"SC-Depth (ResNet18)","rank_in_archive_order":67,"of":79,"metrics":{"Delta < 1.25":"0.863","Delta < 1.25^2":"0.957","Delta < 1.25^3":"0.981","RMSE":"4.950","RMSE log":"0.197","absolute relative error":"0.119"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2-4","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2 self-supervised","model":"Bian et al","rank_in_archive_order":6,"of":8,"metrics":{"Absolute relative error (AbsRel)":"0.157","Root mean square error (RMSE)":"0.593","delta_1":"78.0","delta_2":"94.0","delta_3":"98.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.11610","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}