{"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/rgcnn-regularized-graph-cnn-for-point-cloud","title":"RGCNN: Regularized Graph CNN for Point Cloud Segmentation","arxiv_id":"1806.02952","date":"2018-06-08","proceeding":null,"authors":["Gusi Te","Wei Hu","Zongming Guo","Amin Zheng"],"abstract":"Point cloud, an efficient 3D object representation, has become popular with\nthe development of depth sensing and 3D laser scanning techniques. It has\nattracted attention in various applications such as 3D tele-presence,\nnavigation for unmanned vehicles and heritage reconstruction. The understanding\nof point clouds, such as point cloud segmentation, is crucial in exploiting the\ninformative value of point clouds for such applications. Due to the\nirregularity of the data format, previous deep learning works often convert\npoint clouds to regular 3D voxel grids or collections of images before feeding\nthem into neural networks, which leads to voluminous data and quantization\nartifacts. In this paper, we instead propose a regularized graph convolutional\nneural network (RGCNN) that directly consumes point clouds. Leveraging on\nspectral graph theory, we treat features of points in a point cloud as signals\non graph, and define the convolution over graph by Chebyshev polynomial\napproximation. In particular, we update the graph Laplacian matrix that\ndescribes the connectivity of features in each layer according to the\ncorresponding learned features, which adaptively captures the structure of\ndynamic graphs. Further, we deploy a graph-signal smoothness prior in the loss\nfunction, thus regularizing the learning process. Experimental results on the\nShapeNet part dataset show that the proposed approach significantly reduces the\ncomputational complexity while achieving competitive performance with the state\nof the art. Also, experiments show RGCNN is much more robust to both noise and\npoint cloud density in comparison with other methods. We further apply RGCNN to\npoint cloud classification and achieve competitive results on ModelNet40\ndataset.","url_abs":"http://arxiv.org/abs/1806.02952v1","url_pdf":"http://arxiv.org/pdf/1806.02952v1.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":"rgcnn-regularized-graph-cnn-for-point-cloud","repo_url":"https://github.com/tegusi/RGCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02952"}},"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/tegusi/RGCNN","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"db7e679ad6aa0322","entry":"genData","repo":"tegusi/RGCNN","repo_kind":"listed","path":"train_tf.py","file_url":"https://github.com/tegusi/RGCNN/blob/HEAD/train_tf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"db7e679ad6aa0322"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}