{"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/what-matters-for-3d-scene-flow-network","title":"What Matters for 3D Scene Flow Network","arxiv_id":"2207.09143","date":"2022-07-19","proceeding":null,"authors":["Guangming Wang","Yunzhe Hu","Zhe Liu","Yiyang Zhou","Masayoshi Tomizuka","Wei Zhan","Hesheng Wang"],"abstract":"3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://github.com/IRMVLab/3DFlow.","url_abs":"https://arxiv.org/abs/2207.09143v1","url_pdf":"https://arxiv.org/pdf/2207.09143v1.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":"what-matters-for-3d-scene-flow-network","repo_url":"https://github.com/irmvlab/3dflow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"scene-flow-estimation","task_name":"Scene Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.09143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09143"}},"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":"deterministic:regex_extraction","url":"https://github.com/IRMVLab/3DFlow","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"5aeab7a823d21f0f","entry":"evaluate_2d","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"evaluation_utils.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/evaluation_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":"5aeab7a823d21f0f"}},{"code_sha256_prefix":"cfb929a257ccd28f","entry":"evaluate_3d","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"evaluation_utils.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/evaluation_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":"cfb929a257ccd28f"}},{"code_sha256_prefix":"f05bbacf16ae9dd9","entry":"evaluate_3d_mask","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"evaluation_utils.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/evaluation_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":"f05bbacf16ae9dd9"}},{"code_sha256_prefix":"6413b2b536ff6771","entry":"knn_point","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"pointconv_util.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/pointconv_util.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":"6413b2b536ff6771"}},{"code_sha256_prefix":"6b42e89816dc50e9","entry":"multiScaleLoss","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"models.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/models.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":"6b42e89816dc50e9"}},{"code_sha256_prefix":"ba5d550ea86e437f","entry":"multiScaleLoss","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"models_occlusion.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/models_occlusion.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":"ba5d550ea86e437f"}},{"code_sha256_prefix":"fd8ada46834f05aa","entry":"postprocess","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"cmd_args.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/cmd_args.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":"fd8ada46834f05aa"}},{"code_sha256_prefix":"ca593fc52a89c6a0","entry":"query_yes_no","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"main_utils.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/main_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":"ca593fc52a89c6a0"}},{"code_sha256_prefix":"60f32bcfa7d043b5","entry":"square_distance","repo":"IRMVLab/3DFlow","repo_kind":"official","path":"pointconv_util.py","file_url":"https://github.com/IRMVLab/3DFlow/blob/HEAD/pointconv_util.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":"60f32bcfa7d043b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}