Rethinking Range View Representation for LiDAR Segmentation
Open paper
Benchmark
Model
Rank
Results
3d-semantic-segmentation-on-semantickitti
RangeFormer
–
test mIoU: 73.3%
val mIoU: 67.6%
lidar-semantic-segmentation-on-nuscenes
RangeFormer
–
test mIoU: 0.81
Rank counts only results with a code link.