{"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/191111236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","arxiv_id":"1911.11236","date":"2019-11-25","proceeding":"CVPR 2020 6","authors":["Qingyong Hu","Bo Yang","Linhai Xie","Stefano Rosa","Yulan Guo","Zhihua Wang","Niki Trigoni","Andrew Markham"],"abstract":"We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.","url_abs":"https://arxiv.org/abs/1911.11236v3","url_pdf":"https://arxiv.org/pdf/1911.11236v3.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":"191111236","repo_url":"https://github.com/QingyongHu/RandLA-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"191111236","repo_url":"https://github.com/aRI0U/RandLA-Net-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"191111236","repo_url":"https://github.com/idsia-robotics/RandLA-Net-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"191111236","repo_url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"191111236","repo_url":"https://github.com/tsunghan-wu/randla-net-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"191111236","repo_url":"https://github.com/MindSpore-scientific/code-10/tree/main/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"191111236","repo_url":"https://github.com/MindSpore-scientific/code-8/tree/main/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"191111236","repo_url":"https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/RandLA-Net_Mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"191111236","repo_url":"https://github.com/intel-isl/Open3D-ML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"RandLA-Net","rank_in_archive_order":30,"of":45,"metrics":{"test mIoU":"53.9%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-toronto-3d","task":"3D Semantic Segmentation","dataset":"Toronto-3D","model":"RandLANet","rank_in_archive_order":2,"of":7,"metrics":{"OA":"93.50","mIoU":"68.40"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"RandLA-Net","rank_in_archive_order":52,"of":54,"metrics":{"Number of params":"1.2M","Params (M)":"1.2","mAcc":"81.5","mIoU":"68.5","oAcc":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-semantic3d","task":"Semantic Segmentation","dataset":"Semantic3D","model":"RandLA-Net","rank_in_archive_order":4,"of":17,"metrics":{"mIoU":"77.4%","oAcc":"94.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-toronto-3d-l002","task":"Semantic Segmentation","dataset":"Toronto-3D L002","model":"RandLA-Net","rank_in_archive_order":3,"of":5,"metrics":{"mIoU":"74.3","oAcc":"88.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.11236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.11236"}},"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/MindSpore-scientific/code-8/tree/main/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/QingyongHu/RandLA-Net","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel-isl/Open3D-ML","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idsia-robotics/RandLA-Net-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsunghan-wu/randla-net-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/RandLA-Net_Mindspore","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aRI0U/RandLA-Net-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-10/tree/main/rand_conv-master","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"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":"89cdbfea9999106d","entry":"load_label","repo":"tsunghan-mama/RandLA-Net-pytorch","repo_kind":"listed","path":"evaluate_SemanticKITTI.py","file_url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch/blob/HEAD/evaluate_SemanticKITTI.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89cdbfea9999106d"}},{"code_sha256_prefix":"3bade2b4e07dcaa4","entry":"compute_acc","repo":"tsunghan-mama/RandLA-Net-pytorch","repo_kind":"listed","path":"utils/metric.py","file_url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch/blob/HEAD/utils/metric.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":"3bade2b4e07dcaa4"}},{"code_sha256_prefix":"53945af353c77c7d","entry":"compute_loss","repo":"tsunghan-mama/RandLA-Net-pytorch","repo_kind":"listed","path":"network/loss_func.py","file_url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch/blob/HEAD/network/loss_func.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":"53945af353c77c7d"}},{"code_sha256_prefix":"0ad12b1e8408e2f9","entry":"set_bn_momentum_default","repo":"tsunghan-mama/RandLA-Net-pytorch","repo_kind":"listed","path":"network/pytorch_utils.py","file_url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch/blob/HEAD/network/pytorch_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":"0ad12b1e8408e2f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}