GMA

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision5 results

Optical Flow EstimationonSintel-clean
Average End-Point Error· 2021-04-06
1.388
best: 0.963 (MEMFOF-L)
SOTA
Learning to Estimate Hidden Motions with Global Motion Aggregation arXiv:2104.02409
Optical Flow EstimationonSintel-final
Average End-Point Error· 2021-04-06
2.47
best: 1.907 (MEMFOF-L)
SOTA
Learning to Estimate Hidden Motions with Global Motion Aggregation arXiv:2104.02409
Optical Flow EstimationonKITTI 2015 (train)
EPE· 2021-04-06
4.69
best: 13.17 (HD3)
Learning to Estimate Hidden Motions with Global Motion Aggregation arXiv:2104.02409
Optical Flow EstimationonKITTI 2015 (train)
F1-all· 2021-04-06
17.1
best: 33.7 (PWC-Net)
Learning to Estimate Hidden Motions with Global Motion Aggregation arXiv:2104.02409
Optical Flow EstimationonSpring
1px total· 2021-04-06
7.074
best: 82.265 (PWCNet)
Learning to Estimate Hidden Motions with Global Motion Aggregation arXiv:2104.02409