Papers › PointMixer: MLP-Mixer for Point Cloud Understanding

PointMixer: MLP-Mixer for Point Cloud Understanding

22 Nov 2021arXiv:2111.11187archive 2025-07-28

Jaesung Choe, Chunghyun Park, Francois Rameau, Jaesik Park, In So Kweon

MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer. Despite its simplicity compared to transformer, the concept of channel-mixing MLPs and token-mixing MLPs achieves noticeable performance in visual recognition tasks. Unlike images, point clouds are inherently sparse, unordered and irregular, which limits the direct use of MLP-Mixer for point cloud understanding. In this paper, we propose PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D points. By simply replacing token-mixing MLPs with a softmax function, PointMixer can "mix" features within/between point sets. By doing so, PointMixer can be broadly used in the network as inter-set mixing, intra-set mixing, and pyramid mixing. Extensive experiments show the competitive or superior performance of PointMixer in semantic segmentation, classification, and point reconstruction against transformer-based methods.

PaperPDFCode

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

Code

lifebeyondexpectations/eccv22-pointmixer officialmentioned in papermentioned on GitHubpytorch report
LifeBeyondExpectations/PointMixer officialmentioned on GitHubpytorch report
hrisi/tree-species-classification mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

3D Object Classification3D Point Cloud ClassificationPoint cloud reconstructionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 PointMixer Mean Accuracy 91.4 #52 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointMixer Number of params 6.5M #52 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointMixer Overall Accuracy 93.6 #52 of 111 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointMixer Number of params 6.5M #27 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointMixer mAcc 77.4 #27 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 PointMixer mIoU 71.4 #27 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

Average PoolingDense ConnectionsDropoutGlobal Average PoolingLayer NormalizationMLP-MixerResidual ConnectionSoftmax

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