📊 Showing 4 results | 📏 Metric: mIoU
| Rank | Model | Paper | mIoU | Date | Code |
|---|---|---|---|---|---|
| 1 | Cylinder3D | Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation | 40.07 | 2020-08-04 | 📦 xinge008/Cylinder3D 📦 hongfz16/DS-Net 📦 L-Reichardt/Cylinder3D-updated-CUDA |
| 2 | SPVCNN | Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution | 36.78 | 2020-07-31 | 📦 Pointcept/Pointcept 📦 mit-han-lab/torchsparse 📦 mit-han-lab/spvnas |
| 3 | MinkUNet | 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks | 36.53 | 2019-04-18 | 📦 NVIDIA/MinkowskiEngine 📦 StanfordVL/MinkowskiEngine 📦 Pointcept/Pointcept |
| 4 | SphereFormer | Spherical Transformer for LiDAR-based 3D Recognition | 33.97 | 2023-03-22 | 📦 dvlab-research/sphereformer 📦 dvlab-research/mask-attention-free-transformer |