{"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/deep-ordinal-regression-network-for-monocular","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","arxiv_id":"1806.02446","date":"2018-06-06","proceeding":"CVPR 2018 6","authors":["Huan Fu","Mingming Gong","Chaohui Wang","Kayhan Batmanghelich","DaCheng Tao"],"abstract":"Monocular depth estimation, which plays a crucial role in understanding 3D\nscene geometry, is an ill-posed problem. Recent methods have gained significant\nimprovement by exploring image-level information and hierarchical features from\ndeep convolutional neural networks (DCNNs). These methods model depth\nestimation as a regression problem and train the regression networks by\nminimizing mean squared error, which suffers from slow convergence and\nunsatisfactory local solutions. Besides, existing depth estimation networks\nemploy repeated spatial pooling operations, resulting in undesirable\nlow-resolution feature maps. To obtain high-resolution depth maps,\nskip-connections or multi-layer deconvolution networks are required, which\ncomplicates network training and consumes much more computations. To eliminate\nor at least largely reduce these problems, we introduce a spacing-increasing\ndiscretization (SID) strategy to discretize depth and recast depth network\nlearning as an ordinal regression problem. By training the network using an\nordinary regression loss, our method achieves much higher accuracy and\n\\dd{faster convergence in synch}. Furthermore, we adopt a multi-scale network\nstructure which avoids unnecessary spatial pooling and captures multi-scale\ninformation in parallel.\n  The method described in this paper achieves state-of-the-art results on four\nchallenging benchmarks, i.e., KITTI [17], ScanNet [9], Make3D [50], and NYU\nDepth v2 [42], and win the 1st prize in Robust Vision Challenge 2018. Code has\nbeen made available at: https://github.com/hufu6371/DORN.","url_abs":"http://arxiv.org/abs/1806.02446v1","url_pdf":"http://arxiv.org/pdf/1806.02446v1.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":"deep-ordinal-regression-network-for-monocular","repo_url":"https://github.com/hufu6371/DORN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-ordinal-regression-network-for-monocular","repo_url":"https://github.com/dontLoveBugs/DORN_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-ordinal-regression-network-for-monocular","repo_url":"https://github.com/likesum/prdepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-ordinal-regression-network-for-monocular","repo_url":"https://github.com/liviniuk/DORN_depth_estimation_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-ordinal-regression-network-for-monocular","repo_url":"https://github.com/sjsu-smart-lab/Self-supervised-Monocular-Trained-Depth-Estimation-using-Self-attention-and-Discrete-Disparity-Volum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-nyu-depth-v2","task":"Depth Estimation","dataset":"NYU-Depth V2","model":"DORN","rank_in_archive_order":13,"of":17,"metrics":{"RMS":"0.509"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"DORN","rank_in_archive_order":42,"of":79,"metrics":{"Delta < 1.25":"0.932","Delta < 1.25^2":"0.984","Delta < 1.25^3":"0.994","RMSE":"2.727","RMSE log":"0.120","absolute relative error":"0.072"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"DORN","rank_in_archive_order":68,"of":85,"metrics":{"RMSE":"0.509"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02446"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sjsu-smart-lab/Self-supervised-Monocular-Trained-Depth-Estimation-using-Self-attention-and-Discrete-Disparity-Volum","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dontLoveBugs/DORN_pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/likesum/prdepth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liviniuk/DORN_depth_estimation_Pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hufu6371/DORN","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"39ca09d7e8e28ca0","entry":"get_metrics","repo":"likesum/prdepth","repo_kind":"listed","path":"prdepth/metric.py","file_url":"https://github.com/likesum/prdepth/blob/HEAD/prdepth/metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39ca09d7e8e28ca0"}},{"code_sha256_prefix":"064f8d8b824e90a0","entry":"mean_diff","repo":"likesum/prdepth","repo_kind":"listed","path":"prdepth/utils.py","file_url":"https://github.com/likesum/prdepth/blob/HEAD/prdepth/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"064f8d8b824e90a0"}},{"code_sha256_prefix":"f4ffd9422266b956","entry":"read_depth","repo":"likesum/prdepth","repo_kind":"listed","path":"prdepth/utils.py","file_url":"https://github.com/likesum/prdepth/blob/HEAD/prdepth/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4ffd9422266b956"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}