SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
Open paper
Benchmark
Model
Rank
Results
robust-3d-semantic-segmentation-on-robo3d
SqueezeSeg (64x2048)
#21
mean Corruption Error (mCE): 164.87%
3d-semantic-segmentation-on-semantickitti
SqueezeSeg
#34
test mIoU: 29.5%
Rank counts only results with a code link.