PTv3 ARKit LabelMaker

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· uses extra data· 2024-10-17
79.8
SOTA
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding arXiv:2410.13924
Semantic SegmentationonScanNet
val mIoU· uses extra data· 2024-10-17
79.1
best: 80.5 (DITR)
SOTA
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding arXiv:2410.13924

Audio2 results

10-shot image generationonScanNet
test mIoU· uses extra data· 2024-10-17
79.8
SOTA
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding arXiv:2410.13924
10-shot image generationonScanNet
val mIoU· uses extra data· 2024-10-17
79.1
best: 80.5 (DITR)
SOTA
ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding arXiv:2410.13924