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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 121–130 of 272 papers

TitleStatusHype
Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation—0
Robust Point Cloud Segmentation with Noisy AnnotationsCode1
Effective Utilisation of Multiple Open-Source Datasets to Improve Generalisation Performance of Point Cloud Segmentation Models—0
PointResNet: Residual Network for 3D Point Cloud Segmentation and Classification—0
Learning Latent Part-Whole Hierarchies for Point Clouds—0
Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations—0
Zero-shot point cloud segmentation by transferring geometric primitivesCode0
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud SegmentationCode1
Effective Early Stopping of Point Cloud Neural Networks—0
Show:102550
← PrevPage 13 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