Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
Open paper
Benchmark
Model
Rank
Results
3d-instance-segmentation-on-scannet200-test
CSC-Pretrain Inst.
#5
AP50: 20.9
3d-semantic-segmentation-on-scannet200
CSC
#14
val mIoU: 26.4
test mIoU: 24.9
semantic-segmentation-on-s3dis-area5
CSC+MinkUNet
#17
mIoU: 72.2
Rank counts only results with a code link.