{"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/pwoc-3d-deep-occlusion-aware-end-to-end-scene","title":"PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation","arxiv_id":"1904.06116","date":"2019-04-12","proceeding":null,"authors":["Rohan Saxena","René Schuster","Oliver Wasenmüller","Didier Stricker"],"abstract":"In the last few years, convolutional neural networks (CNNs) have demonstrated\nincreasing success at learning many computer vision tasks including dense\nestimation problems such as optical flow and stereo matching. However, the\njoint prediction of these tasks, called scene flow, has traditionally been\ntackled using slow classical methods based on primitive assumptions which fail\nto generalize. The work presented in this paper overcomes these drawbacks\nefficiently (in terms of speed and accuracy) by proposing PWOC-3D, a compact\nCNN architecture to predict scene flow from stereo image sequences in an\nend-to-end supervised setting. Further, large motion and occlusions are\nwell-known problems in scene flow estimation. PWOC-3D employs specialized\ndesign decisions to explicitly model these challenges. In this regard, we\npropose a novel self-supervised strategy to predict occlusions from images\n(learned without any labeled occlusion data). Leveraging several such\nconstructs, our network achieves competitive results on the KITTI benchmark and\nthe challenging FlyingThings3D dataset. Especially on KITTI, PWOC-3D achieves\nthe second place among end-to-end deep learning methods with 48 times fewer\nparameters than the top-performing method.","url_abs":"http://arxiv.org/abs/1904.06116v1","url_pdf":"http://arxiv.org/pdf/1904.06116v1.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":"pwoc-3d-deep-occlusion-aware-end-to-end-scene","repo_url":"https://github.com/dfki-av/pwoc-3d","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"scene-flow-estimation","task_name":"Scene Flow Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"stereo-matching","task_name":"Stereo Matching Hand"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-flow-estimation-on-kitti-2015-scene-1","task":"Scene Flow Estimation","dataset":"KITTI 2015 Scene Flow Test","model":"PWOC-3D","rank_in_archive_order":2,"of":4,"metrics":{"D1-all":"5.13","D2-all":"8.46","Fl-all":"12.96","Runtime (s)":"0.13","SF-all":"15.69"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.06116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06116"}},"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/dfki-av/pwoc-3d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":12,"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":"1f67eea1467aebaa","entry":"ContextNetwork","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"modules.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/modules.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":"1f67eea1467aebaa"}},{"code_sha256_prefix":"fee9a2fca6892a27","entry":"FeaturePyramidNetwork","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"modules.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/modules.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":"fee9a2fca6892a27"}},{"code_sha256_prefix":"1ca3acaeab51cd2c","entry":"SceneFlowEstimator","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"modules.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/modules.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":"1ca3acaeab51cd2c"}},{"code_sha256_prefix":"30adef1baad9e220","entry":"finetuning_loss","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"losses.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/losses.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":"30adef1baad9e220"}},{"code_sha256_prefix":"3bf1984356663fec","entry":"get_ft3d_dataset","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/datasets.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":"3bf1984356663fec"}},{"code_sha256_prefix":"08ca9fdab4094786","entry":"get_kitti_dataset","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/datasets.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":"08ca9fdab4094786"}},{"code_sha256_prefix":"f82a91175fcdb4fa","entry":"get_spring_dataset","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/datasets.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":"f82a91175fcdb4fa"}},{"code_sha256_prefix":"073f8ee6988dd609","entry":"load_kitti_images","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"utils.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/utils.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":"073f8ee6988dd609"}},{"code_sha256_prefix":"a946b59a08ddf4e9","entry":"load_pfm","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"utils.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/utils.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":"a946b59a08ddf4e9"}},{"code_sha256_prefix":"311eef1ba88e22c8","entry":"loss_per_scale","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"losses.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/losses.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":"311eef1ba88e22c8"}},{"code_sha256_prefix":"943cea4c9f6c8d4e","entry":"multi_scale_loss","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"losses.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/losses.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":"943cea4c9f6c8d4e"}},{"code_sha256_prefix":"e54e5bdb1c932798","entry":"read_sfl_file","repo":"dfki-av/pwoc-3d","repo_kind":"official","path":"utils.py","file_url":"https://github.com/dfki-av/pwoc-3d/blob/HEAD/utils.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":"e54e5bdb1c932798"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}