Papers › Point Transformer

Point Transformer

16 Dec 2020ICCV 2021 10arXiv:2012.09164archive 2025-07-28

Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun

Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation, object part segmentation, and object classification. Our Point Transformer design improves upon prior work across domains and tasks. For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.4% on Area 5, outperforming the strongest prior model by 3.3 absolute percentage points and crossing the 70% mIoU threshold for the first time.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

24 repositories listed; official and paper-mentioned ones first.

Pointcept/Pointcept officialmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sonata: Self-Supervised Learning of Reliable Point Representations (arXiv:2503.16429; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-48 mentioned on GitHubmindsporeSyntology: not harvested report
KernelA/pytorch-point-transformer mentioned on GitHubpytorchSyntology: not harvested report
Meowuu7/Point-Transformer mentioned on GitHubpytorchSyntology: not harvested report
POSTECH-CVLab/FastPointTransformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast Point Transformer (arXiv:2112.04702; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
POSTECH-CVLab/point-transformer mentioned on GitHubpytorchSyntology: not harvested report
Sharpiless/Point-Transformer-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
alzmzyy/pointtransformer mentioned on GitHubmindsporeSyntology: not harvested report
lucidrains/point-transformer-pytorch mentioned on GitHubpytorchSyntology: not harvested report
qq456cvb/Point-Transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PCT: Point cloud transformer (arXiv:2012.09688; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
rauleun/point-transformer-tf2 mentioned on GitHubtfSyntology: not harvested report
tkdguraa/point-transformer-tensorflow mentioned on GitHubtfSyntology: not harvested report
gitee.com/gai-shaoyan/mind3d Syntology: not harvested report
2023-MindSpore-1/ms-code-215 mindsporeSyntology: not harvested report
MS-Mind/MS-Code-06 mindsporeSyntology: not harvested report
Mind23-2/MindCode-5 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 mindsporeSyntology: not harvested report
code-implementation1/Code6 mindsporeSyntology: not harvested report
engelnico/point-transformer pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Point Transformer (arXiv:2011.00931; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
gofinge/pointtransformerv2 pytorchSyntology: not harvested report
isl-org/Open3D-ML pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Submanifold Sparse Convolutional Networks (arXiv:1706.01307; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified), PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud (arXiv:1812.04244; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), PointPillars: Fast Encoders for Object Detection from Point Clouds (arXiv:1812.05784; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
jxl152/Point-Transformer pytorchSyntology: not harvested report
lifebeyondexpectations/eccv22-pointmixer pytorchSyntology: not harvested report
sh4175515/PointTransformer mindsporeSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Part Segmentation3D Point Cloud Classification3D Semantic SegmentationGeneral ClassificationImage ClassificationObjectObject DetectionPoint Cloud SegmentationScene SegmentationSegmentationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part PointTransformer Class Average IoU 83.7 #19 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part PointTransformer Instance Average IoU 86.6 #19 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointTransformer Mean Accuracy 90.6 #50 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointTransformer Overall Accuracy 93.7 #50 of 111 Archive leaderboard report
3D Semantic Segmentation S3DIS PointTransformer mIoU (6-Fold) 73.5 #4 of 6 Archive leaderboard report
3D Semantic Segmentation S3DIS PointTransformer mIoU (Area-5) 70.4 #4 of 6 Archive leaderboard report
3D Semantic Segmentation STPLS3D Point transformer mIOU 47.64 #5 of 6 Archive leaderboard report
Point Cloud Segmentation PointCloud-C PointTransformers mean Corruption Error (mCE) 1.049 #7 of 11 Archive leaderboard report
Semantic Segmentation S3DIS PointTransformer Mean IoU 73.5 #17 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointTransformer Number of params 7.8M #17 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointTransformer Params (M) 7.8 #17 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointTransformer mAcc 81.9 #17 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointTransformer oAcc 90.2 #17 of 54 Archive leaderboard report
Semantic Segmentation S3DIS KPConv Mean IoU 70.6 #24 of 54 Archive leaderboard report
Semantic Segmentation S3DIS KPConv Number of params 14.1M #24 of 54 Archive leaderboard report
Semantic Segmentation S3DIS KPConv Params (M) 14.1 #24 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointCNN Mean IoU 65.4 #36 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointCNN Number of params N/A #36 of 54 Archive leaderboard report
Semantic Segmentation S3DIS SPGraph Mean IoU 62.1 #42 of 54 Archive leaderboard report
Semantic Segmentation S3DIS SPGraph Number of params N/A #42 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointNet Mean IoU 47.6 #51 of 54 Archive leaderboard report
Semantic Segmentation S3DIS PointNet Number of params N/A #51 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointTransformer Number of params 7.8M #32 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointTransformer mAcc 76.5 #32 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointTransformer mIoU 70.4 #32 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointTransformer oAcc 90.8 #32 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointCNN Number of params N/A #53 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointCNN mIoU 57.3 #53 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointNet Number of params N/A #56 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointNet mIoU 41.1 #56 of 61 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections