SOTAVerified

3D Semantic Segmentation

3D Semantic Segmentation is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 348 papers

TitleStatusHype
LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point CloudsCode1
GS4: Generalizable Sparse Splatting Semantic SLAM—0
Point-MoE: Towards Cross-Domain Generalization in 3D Semantic Segmentation via Mixture-of-Experts—0
seg_3D_by_PC2D: Multi-View Projection for Domain Generalization and Adaptation in 3D Semantic SegmentationCode0
MFSeg: Efficient Multi-frame 3D Semantic Segmentation—0
3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation—0
Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding—0
Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation—0
RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration—0
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation—0
Show:102550
← PrevPage 1 of 35Next →
All datasetsSemanticKITTIScanNet200DALESKITTI-360ScanNetSensatUrbanToronto-3DPartNetS3DISScribbleKITTISTPLS3DRELLIS-3D Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Superpoint TransformermIoU (6-Fold)76—Unverified
2OneFormer3DmIoU (Area-5)72.4—Unverified
3PointTransformerV2mIoU (Area-5)71.6—Unverified
4PointNextmIoU (Area-5)70.5—Unverified
5PointTransformermIoU (Area-5)70.4—Unverified
6PVCNN++mIoU (6-Fold)58.98—Unverified