O-CNN

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Medical2 results

Semantic SegmentationonScanNet
test mIoU· 2017-12-05
76.2
best: 79.8 (PTv3 ARKit LabelMaker)
SOTA
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis arXiv:1712.01537
Semantic SegmentationonScanNet
val mIoU· 2017-12-05
74
best: 80.5 (DITR)
SOTA
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis arXiv:1712.01537

Audio2 results

10-shot image generationonScanNet
test mIoU· 2017-12-05
76.2
best: 79.8 (PTv3 ARKit LabelMaker)
SOTA
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis arXiv:1712.01537
10-shot image generationonScanNet
val mIoU· 2017-12-05
74
best: 80.5 (DITR)
SOTA
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis arXiv:1712.01537