JS3C-Net

Reported on 4 benchmarks across 4 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

3D ReconstructiononSemanticKITTI
mIoU· 2020-12-07
23.8
best: 37.9 (TALoS)
SOTA
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion arXiv:2012.03762
3DonSemanticKITTI
mIoU· 2020-12-07
23.8
best: 37.9 (TALoS)
SOTA
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion arXiv:2012.03762

Computer Vision2 results

3D Semantic Scene CompletiononSemanticKITTI
mIoU· 2020-12-07
23.8
best: 37.9 (TALoS)
SOTA
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion arXiv:2012.03762
LIDAR Semantic SegmentationonnuScenes
test mIoU· 2020-12-07
0.74
best: 0.851 (DITR)
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion arXiv:2012.03762