{"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/wasserstein-distances-for-stereo-disparity","title":"Wasserstein Distances for Stereo Disparity Estimation","arxiv_id":"2007.03085","date":"2020-07-06","proceeding":"NeurIPS 2020 12","authors":["Divyansh Garg","Yan Wang","Bharath Hariharan","Mark Campbell","Kilian Q. Weinberger","Wei-Lun Chao"],"abstract":"Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.","url_abs":"https://arxiv.org/abs/2007.03085v2","url_pdf":"https://arxiv.org/pdf/2007.03085v2.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":"wasserstein-distances-for-stereo-disparity","repo_url":"https://github.com/Div99/W-Stereo-Disp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"3d-object-detection-from-stereo-images","task_name":"3D Object Detection From Stereo Images"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"stereo-depth-estimation","task_name":"Stereo Depth Estimation"},{"task_slug":"stereo-disparity-estimation","task_name":"Stereo Disparity Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-from-stereo-images-on-1","task":"3D Object Detection From Stereo Images","dataset":"KITTI Cars Moderate","model":"CDN-DSGN","rank_in_archive_order":3,"of":12,"metrics":{"AP75":"54.2"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-depth-estimation-on-kitti2015","task":"Stereo Depth Estimation","dataset":"KITTI2015","model":"CDN-GANet Deep","rank_in_archive_order":3,"of":7,"metrics":{"three pixel error":"1.92"},"uses_additional_data":false},{"leaderboard":"/sota/stereo-disparity-estimation-on-scene-flow","task":"Stereo Disparity Estimation","dataset":"Scene Flow","model":"CDN-GANet Deep","rank_in_archive_order":4,"of":7,"metrics":{"EPE":"0.7","one pixel error":"7.7","three pixel error":"2.98"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.03085","atlas_url":"https://app.syntology.ai/?focus=2007.03085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03085"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/Div99/W-Stereo-Disp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":"ac269a0e4b8d946e","entry":"default_loader","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/KITTILoader_dataset3d.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/KITTILoader_dataset3d.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac269a0e4b8d946e"}},{"code_sha256_prefix":"ab4109634b75ef8b","entry":"is_image_file","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/KITTILoader3D.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/KITTILoader3D.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab4109634b75ef8b"}},{"code_sha256_prefix":"74a08f63b12add42","entry":"dataloader","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/KITTILoader3D.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/KITTILoader3D.py","link_basis":"first_harvest_node","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":"74a08f63b12add42"}},{"code_sha256_prefix":"0b3ce8456d675a8c","entry":"default_loader","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/SceneFlowLoader.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/SceneFlowLoader.py","link_basis":"first_harvest_node","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":"0b3ce8456d675a8c"}},{"code_sha256_prefix":"8d9f5f6ce951aa15","entry":"disparity_loader","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/KITTILoader_dataset3d.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/KITTILoader_dataset3d.py","link_basis":"first_harvest_node","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":"8d9f5f6ce951aa15"}},{"code_sha256_prefix":"aaf877e27c4a3c3e","entry":"disparity_loader","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/SceneFlowLoader.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/SceneFlowLoader.py","link_basis":"first_harvest_node","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":"aaf877e27c4a3c3e"}},{"code_sha256_prefix":"b9ee501ff15b4629","entry":"dynamic_baseline","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/KITTI_submission_loader.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/KITTI_submission_loader.py","link_basis":"first_harvest_node","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":"b9ee501ff15b4629"}},{"code_sha256_prefix":"aaea02c311c902eb","entry":"readPFM","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/readpfm.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/readpfm.py","link_basis":"first_harvest_node","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":"aaea02c311c902eb"}},{"code_sha256_prefix":"e18b9288494dc86a","entry":"read_calib_file","repo":"Div99/W-Stereo-Disp","repo_kind":"official","path":"src/disp_dataloader/KITTI_submission_loader.py","file_url":"https://github.com/Div99/W-Stereo-Disp/blob/HEAD/src/disp_dataloader/KITTI_submission_loader.py","link_basis":"first_harvest_node","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":"e18b9288494dc86a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}