ARFlow-MV

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Computer Vision4 results

Optical Flow EstimationonKITTI 2012 unsupervised
Average End-Point Error· 2020-03-29
1.5
best: 1.4 (UpFlow)
SOTA
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation arXiv:2003.13045
Optical Flow EstimationonSintel Clean unsupervised
Average End-Point Error· 2020-03-29
4.49
best: 4.16 (MDFlow)
SOTA
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation arXiv:2003.13045
Optical Flow EstimationonSintel Final unsupervised
Average End-Point Error· 2020-03-29
5.67
best: 5.32 (UpFlow)
SOTA
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation arXiv:2003.13045
Optical Flow EstimationonKITTI 2015 unsupervised
Fl-all· 2020-03-29
11.79
SOTA
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation arXiv:2003.13045