FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

CVPR 2017 Eddy IlgNikolaus MayerTonmoy SaikiaMargret KeuperAlexey DosovitskiyThomas Brox

The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Dense Pixel Correspondence Estimation HPatches FlowNet2 Viewpoint I AEPE 5.99 # 4
Dense Pixel Correspondence Estimation HPatches FlowNet2 Viewpoint II AEPE 15.55 # 4
Dense Pixel Correspondence Estimation HPatches FlowNet2 Viewpoint III AEPE 17.09 # 4
Dense Pixel Correspondence Estimation HPatches FlowNet2 Viewpoint IV AEPE 22.13 # 4
Dense Pixel Correspondence Estimation HPatches FlowNet2 Viewpoint V AEPE 30.68 # 4
Skeleton Based Action Recognition JHMDB Pose Tracking FlowNet2 [email protected] 45.2 # 2
Skeleton Based Action Recognition JHMDB Pose Tracking FlowNet2 [email protected] 62.9 # 3
Skeleton Based Action Recognition JHMDB Pose Tracking FlowNet2 [email protected] 73.5 # 3
Skeleton Based Action Recognition JHMDB Pose Tracking FlowNet2 [email protected] 80.6 # 3
Skeleton Based Action Recognition JHMDB Pose Tracking FlowNet2 [email protected] 85.5 # 3