{"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/pointcnn-convolution-on-mathcalx-transformed","title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","arxiv_id":"1801.07791","date":"2018-01-23","proceeding":"NeurIPS 2018","authors":["Yangyan Li","Rui Bu","Mingchao Sun","Wei Wu","Xinhan Di","Baoquan Chen"],"abstract":"We present a simple and general framework for feature learning from point\nclouds. The key to the success of CNNs is the convolution operator that is\ncapable of leveraging spatially-local correlation in data represented densely\nin grids (e.g. images). However, point clouds are irregular and unordered, thus\ndirectly convolving kernels against features associated with the points, will\nresult in desertion of shape information and variance to point ordering. To\naddress these problems, we propose to learn an $\\mathcal{X}$-transformation\nfrom the input points, to simultaneously promote two causes. The first is the\nweighting of the input features associated with the points, and the second is\nthe permutation of the points into a latent and potentially canonical order.\nElement-wise product and sum operations of the typical convolution operator are\nsubsequently applied on the $\\mathcal{X}$-transformed features. The proposed\nmethod is a generalization of typical CNNs to feature learning from point\nclouds, thus we call it PointCNN. Experiments show that PointCNN achieves on\npar or better performance than state-of-the-art methods on multiple challenging\nbenchmark datasets and tasks.","url_abs":"http://arxiv.org/abs/1801.07791v5","url_pdf":"http://arxiv.org/pdf/1801.07791v5.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":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/yangyanli/PointCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/LebronGG/PointCnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/Lw510107/PointCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/agarret7/PointCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/c3210927/point_cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/chinakook/PointCNN.MX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/dream-chaser/pointcnn_for_3DFER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/hxdengBerkeley/PointCNN.Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/lanlan96/3drm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/luost26/diffusion-point-cloud","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/nicolas-chaulet/torch-points3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/octree-nn/ocnn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/pyg-team/pytorch_geometric","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/tch/pointcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/tschattschneider/pointcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pointcnn-convolution-on-mathcalx-transformed","repo_url":"https://github.com/NMADALI97/PointCNN_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-instance-segmentation-on-s3dis","task":"3D Instance Segmentation","dataset":"S3DIS","model":"PointCNN","rank_in_archive_order":21,"of":21,"metrics":{"mAcc":"75.61","mIoU":"65.39%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-part-segmentation-on-intra","task":"3D Part Segmentation","dataset":"IntrA","model":"PointCNN","rank_in_archive_order":4,"of":7,"metrics":{"DSC (A)":"81.74","DSC (V)":"96.62","IoU (A)":"74.11","IoU (V)":"93.59"},"uses_additional_data":false},{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"PointCNN","rank_in_archive_order":35,"of":67,"metrics":{"Class Average IoU":"84.6","Instance Average IoU":"86.14"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"PointCNN","rank_in_archive_order":72,"of":77,"metrics":{"Mean Accuracy":"75.1","OBJ-BG (OA)":"86.1","OBJ-ONLY (OA)":"85.5","Overall Accuracy":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-1","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (10-shot)","model":"PointCNN","rank_in_archive_order":25,"of":30,"metrics":{"Overall Accuracy":"65.41","Standard Deviation":"8.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.07791","atlas_url":"https://app.syntology.ai/?focus=1801.07791","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":"1801.07791"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.07791\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.07791"},"call":"get_concepts_for_paper(arxiv_id=\"1801.07791\")"}],"by_repo":[{"repo":"yangyanli/PointCNN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"LebronGG/PointCnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Lw510107/PointCNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"agarret7/PointCNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"c3210927/point_cnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"chinakook/PointCNN.MX","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dream-chaser/pointcnn_for_3DFER","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hxdengBerkeley/PointCNN.Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lanlan96/3drm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"luost26/diffusion-point-cloud","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.01458"],"harvested_for_calls":[{"arxiv_id":"2103.01458","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.01458"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.01458\")"}]},{"repo":"nicolas-chaulet/torch-points3d","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"octree-nn/ocnn-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pyg-team/pytorch_geometric","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2606.17022"],"harvested_for_calls":[{"arxiv_id":"2606.17022","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2606.17022"},"call":"get_harvested_code_for_paper(arxiv_id=\"2606.17022\")"}]},{"repo":"tch/pointcnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tschattschneider/pointcnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"NMADALI97/PointCNN_Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"5f2ac2c1cc8e18fcbc8120e88bfd6b1d0dfdbfa4cf1eb8fef8d96d2145bedce6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}