OpenCodePapers

semantic-segmentation-on-semantic3d

Semantic Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodemIoUoAccModelNameReleaseDate
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling✓ Link78.2%93.6Feature Geometric Net2020-12-17
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning✓ Link77.8%RFCR2021-05-21
SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation✓ Link77.6%94.7%SCF-Net2021-06-19
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds✓ Link77.4%94.8RandLA-Net2019-11-25
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs✓ Link76.2%92.9%SPG2017-11-27
Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion✓ Link75.4%94.9%BAAF-Net2021-03-12
KPConv: Flexible and Deformable Convolution for Point Clouds✓ Link74.6%KPConv2019-04-18
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs✓ Link73.2%SPG2017-11-27
Graph Attention Convolution for Point Cloud Semantic Segmentation✓ Link70.8%GACNet2019-06-01
ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics✓ Link69.3%shellnet_v22019-08-17
Classification of Point Cloud Scenes with Multiscale Voxel Deep Network✓ Link65.3%MSDeepVoxNet2018-04-10
Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods62.7%RF_MSSF2018-08-01
SEGCloud: Semantic Segmentation of 3D Point Clouds61.3%SegCloud2017-10-20
Unstructured point cloud semantic labelingusing deep segmentation networks✓ Link59.1%SnapNet_2017-04-23
Deep Projective 3D Semantic Segmentation✓ Link58.5%DeePr3SS2017-05-09
SEGCloud: Semantic Segmentation of 3D Point Clouds58.2%3D-FCNN-TI2017-10-20
Fast semantic segmentation of 3d point clouds with strongly varying density54.2%TMLC-MSR2016-03-07
Check out how to contribute new results.