Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

CVPR 2019  ·  Junhwa Hur, Stefan 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. While leading to more accurate results, the downside of this is an increased number of parameters. Taking inspiration from both classical energy minimization approaches as well as residual networks, we propose an iterative residual refinement (IRR) scheme based on weight sharing that can be combined with several backbone networks. It reduces the number of parameters, improves the accuracy, or even achieves both. Moreover, we show that integrating occlusion prediction and bi-directional flow estimation into our IRR scheme can further boost the accuracy. Our full network achieves state-of-the-art results for both optical flow and occlusion estimation across several standard datasets.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Optical Flow Estimation KITTI 2012 IRR-PWC Average End-Point Error 1.6 # 10
Optical Flow Estimation KITTI 2015 IRR-PWC Fl-all 7.65 # 10
Optical Flow Estimation Sintel-clean IRR-PWC Average End-Point Error 3.84 # 21
Optical Flow Estimation Sintel-final IRR-PWC Average End-Point Error 4.579 # 19

Methods


No methods listed for this paper. Add relevant methods here