EdgeNet (SUNCG pretraining)

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Methodology2 results

3D ReconstructiononNYUv2
mIoU· uses extra data· 2021-03-12
33.7
best: 55.4 (SG-SSC)
3D Semantic Scene Completion: a Survey arXiv:2103.07466
3DonNYUv2
mIoU· uses extra data· 2021-03-12
33.7
best: 55.4 (SG-SSC)
3D Semantic Scene Completion: a Survey arXiv:2103.07466

Computer Vision1 result

3D Semantic Scene CompletiononNYUv2
mIoU· uses extra data· 2021-03-12
33.7
best: 55.4 (SG-SSC)
3D Semantic Scene Completion: a Survey arXiv:2103.07466