Robust 3D Semantic Segmentation On Wod C
Metrics
mean Corruption Error (mCE)
Results
Performance results of various models on this benchmark
Model Name | mean Corruption Error (mCE) | Paper Title | Repository |
|---|---|---|---|
| Cylinder3D (torchsparse) | 106.02% | Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation | |
| SPVCNN-18 | 103.60% | Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution | |
| MinkUNet-18 | 100.00% | 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks | |
| SPVCNN-34 | 98.72% | Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution | |
| MinkUNet-34 | 96.21% | 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks |
0 of 5 row(s) selected.