ML Research Wiki / Benchmarks / LIDAR Semantic Segmentation / Paris-Lille-3D

Paris-Lille-3D

LIDAR Semantic Segmentation Benchmark

Performance Over Time

📊 Showing 7 results | 📏 Metric: mIOU

Top Performing Models

Rank Model Paper mIOU Date Code
1 FKAConv FKAConv: Feature-Kernel Alignment for Point Cloud Convolution 0.83 2020-04-09 📦 valeoai/FKAConv
2 Feature Geometric Net (FG Net) FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling 0.82 2020-12-17 📦 KangchengLiu/Feature-Geometric-Net-FG-Net
3 GeomGCNN Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks 0.79 2021-03-28 -
4 ConvPoint ConvPoint: Continuous Convolutions for Point Cloud Processing 0.76 2019-04-04 📦 aboulch/ConvPoint
5 KPConv deform KPConv: Flexible and Deformable Convolution for Point Clouds 0.76 2019-04-18 📦 isl-org/Open3D-ML 📦 HuguesTHOMAS/KPConv-PyTorch 📦 HuguesTHOMAS/KPConv
6 ConvPoint_Keras ConvPoint: Continuous Convolutions for Point Cloud Processing 0.72 2019-04-04 📦 aboulch/ConvPoint
7 Paris-Lille-3D Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification 0.31 2017-11-30 -

All Papers (7)

valeoai/FKAConv
KangchengLiu/Feature-Geometric-Net-FG-Net
aboulch/ConvPoint
isl-org/Open3D-ML HuguesTHOMAS/KPConv-PyTorch
aboulch/ConvPoint