{"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/181201711","title":"A Graph-CNN for 3D Point Cloud Classification","arxiv_id":"1812.01711","date":"2018-11-28","proceeding":null,"authors":["Yingxue Zhang","Michael Rabbat"],"abstract":"Graph convolutional neural networks (Graph-CNNs) extend traditional CNNs to\nhandle data that is supported on a graph. Major challenges when working with\ndata on graphs are that the support set (the vertices of the graph) do not\ntypically have a natural ordering, and in general, the topology of the graph is\nnot regular (i.e., vertices do not all have the same number of neighbors).\nThus, Graph-CNNs have huge potential to deal with 3D point cloud data which has\nbeen obtained from sampling a manifold. In this paper, we develop a Graph-CNN\nfor classifying 3D point cloud data, called PointGCN. The architecture combines\nlocalized graph convolutions with two types of graph downsampling operations\n(also known as pooling). By the effective exploration of the point cloud local\nstructure using the Graph-CNN, the proposed architecture achieves competitive\nperformance on the 3D object classification benchmark ModelNet, and our\narchitecture is more stable than competing schemes.","url_abs":"http://arxiv.org/abs/1812.01711v1","url_pdf":"http://arxiv.org/pdf/1812.01711v1.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":"181201711","repo_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.01711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01711"}},"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/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"61cd395237a348ae","entry":"chebyshevCoefficient","repo":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","repo_kind":"official","path":"global_pooling_model/layers.py","file_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification/blob/HEAD/global_pooling_model/layers.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":"61cd395237a348ae"}},{"code_sha256_prefix":"b5f2b8d96b1adb3c","entry":"gcnLayer","repo":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","repo_kind":"official","path":"global_pooling_model/layers.py","file_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification/blob/HEAD/global_pooling_model/layers.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":"b5f2b8d96b1adb3c"}},{"code_sha256_prefix":"de3e0e22ff9c2e6a","entry":"getDataFiles","repo":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","repo_kind":"official","path":"global_pooling_model/utils.py","file_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification/blob/HEAD/global_pooling_model/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":"de3e0e22ff9c2e6a"}},{"code_sha256_prefix":"5316a3f190fed0f1","entry":"loadDataFile","repo":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","repo_kind":"official","path":"global_pooling_model/utils.py","file_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification/blob/HEAD/global_pooling_model/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":"5316a3f190fed0f1"}},{"code_sha256_prefix":"4378e52166c970f0","entry":"load_h5","repo":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","repo_kind":"official","path":"global_pooling_model/utils.py","file_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification/blob/HEAD/global_pooling_model/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":"4378e52166c970f0"}},{"code_sha256_prefix":"241e3c113dc9d6be","entry":"weightVariables","repo":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","repo_kind":"official","path":"global_pooling_model/layers.py","file_url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification/blob/HEAD/global_pooling_model/layers.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":"241e3c113dc9d6be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}