{"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/equivariant-point-cloud-analysis-via-learning","title":"Equivariant Point Cloud Analysis via Learning Orientations for Message Passing","arxiv_id":"2203.14486","date":"2022-03-28","proceeding":"CVPR 2022 1","authors":["Shitong Luo","Jiahan Li","Jiaqi Guan","Yufeng Su","Chaoran Cheng","Jian Peng","Jianzhu Ma"],"abstract":"Equivariance has been a long-standing concern in various fields ranging from computer vision to physical modeling. Most previous methods struggle with generality, simplicity, and expressiveness -- some are designed ad hoc for specific data types, some are too complex to be accessible, and some sacrifice flexible transformations. In this work, we propose a novel and simple framework to achieve equivariance for point cloud analysis based on the message passing (graph neural network) scheme. We find the equivariant property could be obtained by introducing an orientation for each point to decouple the relative position for each point from the global pose of the entire point cloud. Therefore, we extend current message passing networks with a module that learns orientations for each point. Before aggregating information from the neighbors of a point, the networks transforms the neighbors' coordinates based on the point's learned orientations. We provide formal proofs to show the equivariance of the proposed framework. Empirically, we demonstrate that our proposed method is competitive on both point cloud analysis and physical modeling tasks. Code is available at https://github.com/luost26/Equivariant-OrientedMP .","url_abs":"https://arxiv.org/abs/2203.14486v1","url_pdf":"https://arxiv.org/pdf/2203.14486v1.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":"equivariant-point-cloud-analysis-via-learning","repo_url":"https://github.com/luost26/equivariant-orientedmp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.14486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14486"}},"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/luost26/equivariant-orientedmp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":4,"ran_honours":1,"unverified":9},"by_repo_kind":{"official":{"samples":15,"ran":6,"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":"cdd0141594039dcb","entry":"knn","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"models/cls/oriented_dgcnn.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/models/cls/oriented_dgcnn.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cdd0141594039dcb"}},{"code_sha256_prefix":"d26ff18f89e81ea5","entry":"normalize_vector","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"modules/geometric.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/modules/geometric.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d26ff18f89e81ea5"}},{"code_sha256_prefix":"4783fbece52f500e","entry":"pc_normalize","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"datasets/modelnet.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/datasets/modelnet.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4783fbece52f500e"}},{"code_sha256_prefix":"e83f79b6a566bc97","entry":"project_v2v","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"modules/geometric.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/modules/geometric.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e83f79b6a566bc97"}},{"code_sha256_prefix":"be3d8f2945b52b90","entry":"register_model","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"models/cls/_registry.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/models/cls/_registry.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be3d8f2945b52b90"}},{"code_sha256_prefix":"38735f4bca7f8220","entry":"tuple_index","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"modules/gvp.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/modules/gvp.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38735f4bca7f8220"}},{"code_sha256_prefix":"73a932f7826aa350","entry":"calculate_shape_IoU","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"train_partseg.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/train_partseg.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":"73a932f7826aa350"}},{"code_sha256_prefix":"f80066a00e7156a2","entry":"farthest_point_sample","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"datasets/modelnet.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/datasets/modelnet.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":"f80066a00e7156a2"}},{"code_sha256_prefix":"8e1b540b7dbb4fd7","entry":"gather","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"models/cls/oriented_dgcnn.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/models/cls/oriented_dgcnn.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":"8e1b540b7dbb4fd7"}},{"code_sha256_prefix":"d98fb5121c2ad8dd","entry":"get_graph_feature","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"models/cls/oriented_dgcnn.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/models/cls/oriented_dgcnn.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":"d98fb5121c2ad8dd"}},{"code_sha256_prefix":"9bad2eb9e3f5facf","entry":"get_hierarchical_idx","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"modules/frame.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/modules/frame.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":"9bad2eb9e3f5facf"}},{"code_sha256_prefix":"cc0632008d5a9aef","entry":"get_hierarchical_idx","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"models/cls/oriented_rscnn.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/models/cls/oriented_rscnn.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":"cc0632008d5a9aef"}},{"code_sha256_prefix":"be1d33da9ab60900","entry":"get_model","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"models/cls/_registry.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/models/cls/_registry.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":"be1d33da9ab60900"}},{"code_sha256_prefix":"28e463a04d36b65d","entry":"randn","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"modules/gvp.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/modules/gvp.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":"28e463a04d36b65d"}},{"code_sha256_prefix":"e253039723a2f1f8","entry":"safe_norm","repo":"luost26/equivariant-orientedmp","repo_kind":"official","path":"modules/geometric.py","file_url":"https://github.com/luost26/equivariant-orientedmp/blob/HEAD/modules/geometric.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":"e253039723a2f1f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}