Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

CVPR 2019 Junhwa HurStefan Roth

Deep learning approaches to optical flow estimation have seen rapid progress over the recent years. One common trait of many networks is that they refine an initial flow estimate either through multiple stages or across the levels of a coarse-to-fine representation... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Optical Flow Estimation KITTI 2012 IRR-PWC Average End-Point Error 1.6 # 2
Optical Flow Estimation KITTI 2015 IRR-PWC Fl-all 7.65 # 1
Optical Flow Estimation Sintel-clean IRR-PWC Average End-Point Error 3.84 # 4
Optical Flow Estimation Sintel-final IRR-PWC Average End-Point Error 4.579 # 3