{"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/multi-scale-continuous-crfs-as-sequential","title":"Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation","arxiv_id":"1704.02157","date":"2017-04-07","proceeding":"CVPR 2017 7","authors":["Dan Xu","Elisa Ricci","Wanli Ouyang","Xiaogang Wang","Nicu Sebe"],"abstract":"This paper addresses the problem of depth estimation from a single still\nimage. Inspired by recent works on multi- scale convolutional neural networks\n(CNN), we propose a deep model which fuses complementary information derived\nfrom multiple CNN side outputs. Different from previous methods, the\nintegration is obtained by means of continuous Conditional Random Fields\n(CRFs). In particular, we propose two different variations, one based on a\ncascade of multiple CRFs, the other on a unified graphical model. By designing\na novel CNN implementation of mean-field updates for continuous CRFs, we show\nthat both proposed models can be regarded as sequential deep networks and that\ntraining can be performed end-to-end. Through extensive experimental evaluation\nwe demonstrate the effective- ness of the proposed approach and establish new\nstate of the art results on publicly available datasets.","url_abs":"http://arxiv.org/abs/1704.02157v1","url_pdf":"http://arxiv.org/pdf/1704.02157v1.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":"multi-scale-continuous-crfs-as-sequential","repo_url":"https://github.com/danxuhk/ContinuousCRF-CNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-scale-continuous-crfs-as-sequential","repo_url":"https://github.com/xuyingyue/DeepUnifiedCRF_iccv19","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-nyu-depth-v2","task":"Depth Estimation","dataset":"NYU-Depth V2","model":"MS-CRF","rank_in_archive_order":14,"of":17,"metrics":{"RMS":"0.586"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"Xu et al.","rank_in_archive_order":81,"of":85,"metrics":{"RMSE":"0.586"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.02157","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}