CorrNet3D (Trained on Surreal)

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.

Methodology2 results

3DonSHREC'19
Accuracy at 1%· uses extra data· 2020-12-31
6
best: 26.4 (Diffusion 3D Features (Zero-shot))
SOTA
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds arXiv:2012.15638
3DonSHREC'19
Euclidean Mean Error (EME)· uses extra data· 2020-12-31
6.9
best: 1.7 (Diffusion 3D Features (Zero-shot))
SOTA
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds arXiv:2012.15638

Computer Vision2 results

3D Shape RepresentationonSHREC'19
Accuracy at 1%· uses extra data· 2020-12-31
6
best: 26.4 (Diffusion 3D Features (Zero-shot))
SOTA
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds arXiv:2012.15638
3D Shape RepresentationonSHREC'19
Euclidean Mean Error (EME)· uses extra data· 2020-12-31
6.9
best: 1.7 (Diffusion 3D Features (Zero-shot))
SOTA
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds arXiv:2012.15638