{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/190408017","title":"A-CNN: Annularly Convolutional Neural Networks on Point Clouds","arxiv_id":"1904.08017","date":"2019-04-16","proceeding":"CVPR 2019 6","authors":["Artem Komarichev","Zichun Zhong","Jing Hua"],"abstract":"Analyzing the geometric and semantic properties of 3D point clouds through\nthe deep networks is still challenging due to the irregularity and sparsity of\nsamplings of their geometric structures. This paper presents a new method to\ndefine and compute convolution directly on 3D point clouds by the proposed\nannular convolution. This new convolution operator can better capture the local\nneighborhood geometry of each point by specifying the (regular and dilated)\nring-shaped structures and directions in the computation. It can adapt to the\ngeometric variability and scalability at the signal processing level. We apply\nit to the developed hierarchical neural networks for object classification,\npart segmentation, and semantic segmentation in large-scale scenes. The\nextensive experiments and comparisons demonstrate that our approach outperforms\nthe state-of-the-art methods on a variety of standard benchmark datasets (e.g.,\nModelNet10, ModelNet40, ShapeNet-part, S3DIS, and ScanNet).","url_abs":"http://arxiv.org/abs/1904.08017v1","url_pdf":"http://arxiv.org/pdf/1904.08017v1.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":"190408017","repo_url":"https://github.com/artemkomarichev/a-cnn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"A-CNN","rank_in_archive_order":84,"of":111,"metrics":{"Overall Accuracy":"92.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"PointCNN","rank_in_archive_order":35,"of":54,"metrics":{"Mean IoU":"65.4","Number of params":"N/A","oAcc":"88.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"A-CNN","rank_in_archive_order":39,"of":54,"metrics":{"Mean IoU":"62.9","Number of params":"N/A","oAcc":"87.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"SPGraph","rank_in_archive_order":41,"of":54,"metrics":{"Mean IoU":"62.1","Number of params":"N/A","oAcc":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"3P-RNN","rank_in_archive_order":47,"of":54,"metrics":{"Mean IoU":"56.3","Number of params":"N/A","oAcc":"86.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"PointNet","rank_in_archive_order":50,"of":54,"metrics":{"Mean IoU":"47.6","Number of params":"N/A","oAcc":"78.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.08017","atlas_url":"https://app.syntology.ai/?focus=1904.08017","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1904.08017"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.08017\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.08017"},"call":"get_concepts_for_paper(arxiv_id=\"1904.08017\")"}],"by_repo":[{"repo":"artemkomarichev/a-cnn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b070e7a0dce47e27d66042d4248834a4a648fb819fa86193f512a5931939cc2d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}