SOTAVerified

Point Cloud Segmentation

3D point cloud segmentation is the process of classifying point clouds into multiple homogeneous regions, the points in the same region will have the same properties. The segmentation is challenging because of high redundancy, uneven sampling density, and lack explicit structure of point cloud data. This problem has many applications in robotics such as intelligent vehicles, autonomous mapping and navigation.

Source: 3D point cloud segmentation: A survey

Papers

Showing 141–150 of 272 papers

TitleStatusHype
3D-model ShapeNet Core Classification using Meta-Semantic LearningCode0
SemAffiNet: Semantic-Affine Transformation for Point Cloud SegmentationCode1
Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning—0
Point Cloud Semantic Segmentation using Multi Scale Sparse Convolution Neural Network—0
Sequential Point Clouds: A Survey—0
Stratified Transformer for 3D Point Cloud SegmentationCode2
Masked Autoencoders for Point Cloud Self-supervised LearningCode2
Contrastive Boundary Learning for Point Cloud SegmentationCode1
RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep LearningCode1
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP FrameworkCode2
Show:102550
← PrevPage 15 of 28Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OcCo-PCNmean Corruption Error (mCE)1.17—Unverified
2OcCo-PointNetmean Corruption Error (mCE)1.13—Unverified
3PointNet++mean Corruption Error (mCE)1.11—Unverified
4PointTransformersmean Corruption Error (mCE)1.05—Unverified
5PointMLPmean Corruption Error (mCE)0.98—Unverified
6PointMAEmean Corruption Error (mCE)0.93—Unverified
7GDANetmean Corruption Error (mCE)0.92—Unverified
8GDANetmean Corruption Error (mCE)0.89—Unverified