{"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/point-transformer-v2-grouped-vector-attention","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","arxiv_id":"2210.05666","date":"2022-10-11","proceeding":null,"authors":["Xiaoyang Wu","Yixing Lao","Li Jiang","Xihui Liu","Hengshuang Zhao"],"abstract":"As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work. In particular, we first propose group vector attention, which is more effective than the previous version of vector attention. Inheriting the advantages of both learnable weight encoding and multi-head attention, we present a highly effective implementation of grouped vector attention with a novel grouped weight encoding layer. We also strengthen the position information for attention by an additional position encoding multiplier. Furthermore, we design novel and lightweight partition-based pooling methods which enable better spatial alignment and more efficient sampling. Extensive experiments show that our model achieves better performance than its predecessor and achieves state-of-the-art on several challenging 3D point cloud understanding benchmarks, including 3D point cloud segmentation on ScanNet v2 and S3DIS and 3D point cloud classification on ModelNet40. Our code will be available at https://github.com/Gofinge/PointTransformerV2.","url_abs":"https://arxiv.org/abs/2210.05666v2","url_pdf":"https://arxiv.org/pdf/2210.05666v2.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":"point-transformer-v2-grouped-vector-attention","repo_url":"https://github.com/Pointcept/PointTransformerV2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"point-transformer-v2-grouped-vector-attention","repo_url":"https://github.com/Pointcept/Pointcept","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":null,"task_name":"Position"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":null,"task_name":"Semantic Segmentation on ScanNet"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"PTv2","rank_in_archive_order":18,"of":111,"metrics":{"Mean Accuracy":"91.6","Overall Accuracy":"94.2"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-s3dis","task":"3D Semantic Segmentation","dataset":"S3DIS","model":"PointTransformerV2","rank_in_archive_order":2,"of":6,"metrics":{"mIoU (Area-5)":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet-1","task":"3D Semantic Segmentation","dataset":"ScanNet++","model":"PTv2","rank_in_archive_order":8,"of":8,"metrics":{"Top-1 IoU":"0.445","Top-3 IoU":"0.688"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"PTv2","rank_in_archive_order":9,"of":45,"metrics":{"test mIoU":"72.6%","val mIoU":"70.3%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-nuscenes","task":"3D Semantic Segmentation","dataset":"nuScenes","model":"PTv2","rank_in_archive_order":1,"of":3,"metrics":{"mIoU":"82.6%"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"PTv2","rank_in_archive_order":3,"of":36,"metrics":{"test mIoU":"0.826","val mIoU":"0.802"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"PTv2","rank_in_archive_order":18,"of":61,"metrics":{"Number of params":"N/A","mAcc":"78.0","mIoU":"72.6","oAcc":"91.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannet","task":"Semantic Segmentation","dataset":"ScanNet","model":"PTv2","rank_in_archive_order":21,"of":45,"metrics":{"test mIoU":"75.2","val mIoU":"75.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.05666","atlas_url":"https://app.syntology.ai/?focus=2210.05666","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":"2210.05666"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.05666\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.05666"},"call":"get_concepts_for_paper(arxiv_id=\"2210.05666\")"}],"by_repo":[{"repo":"Pointcept/PointTransformerV2","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Pointcept/Pointcept","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.16429"],"harvested_for_calls":[{"arxiv_id":"2503.16429","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.16429"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.16429\")"}]}],"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":"78a333ad7c61caf302e9df513f0de7b8f2e42f38cd0f5163af60b72b07522354","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}