{"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/toward-practical-self-supervised-monocular","title":"Toward Practical Monocular Indoor Depth Estimation","arxiv_id":"2112.02306","date":"2021-12-04","proceeding":"CVPR 2022 1","authors":["Cho-Ying Wu","Jialiang Wang","Michael Hall","Ulrich Neumann","Shuochen Su"],"abstract":"The majority of prior monocular depth estimation methods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we propose a structure distillation approach to learn knacks from an off-the-shelf relative depth estimator that produces structured but metric-agnostic depth. By combining structure distillation with a branch that learns metrics from left-right consistency, we attain structured and metric depth for generic indoor scenes and make inferences in real-time. To facilitate learning and evaluation, we collect SimSIN, a dataset from simulation with thousands of environments, and UniSIN, a dataset that contains about 500 real scan sequences of generic indoor environments. We experiment in both sim-to-real and real-to-real settings, and show improvements, as well as in downstream applications using our depth maps. This work provides a full study, covering methods, data, and applications aspects.","url_abs":"https://arxiv.org/abs/2112.02306v2","url_pdf":"https://arxiv.org/pdf/2112.02306v2.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":"toward-practical-self-supervised-monocular","repo_url":"https://github.com/facebookresearch/DistDepth","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"toward-practical-self-supervised-monocular","repo_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[{"slug":"va","name":"VA (Virtual Apartment)","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2-4","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2 self-supervised","model":"DistDepth","rank_in_archive_order":2,"of":8,"metrics":{"Absolute relative error (AbsRel)":"0.130","Root mean square error (RMSE)":"0.517","delta_1":"83.2","delta_2":"96.3","delta_3":"99.0"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-va","task":"Monocular Depth Estimation","dataset":"VA (Virtual Apartment)","model":"DistDepth","rank_in_archive_order":1,"of":3,"metrics":{"Absolute relative error (AbsRel)":"0.175","Log root mean square error  (RMSE_log)":"0.213","Mean average error (MAE) ":"0.253","Root mean square error (RMSE)":"0.374"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.02306","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}