Graph Laplacian Regularization for Robust Optical Flow Estimation

doi:10.1109/TIP.2019.2945653

Graph Laplacian Regularization for Robust Optical Flow Estimation

2020-01-01

9

PRE

AI

DOI：10.1109/TIP.2019.2945653

Original

Original request for help

Save

Abstract

En 中文

This paper proposes graph Laplacian regularization for robust estimation of optical flow. First, we analyze the spectral properties of dense graph Laplacians and show that dense graphs achieve a better trade-off between preserving flow discontinuities and filtering noise, compared with the usual Laplacian. Using this analysis, we then propose a robust optical flow estimation method based on Gaussian graph Laplacians. We revisit the framework of iteratively reweighted least-squares from the perspective of graph edge reweighting, and employ the Welsch loss function to preserve flow discontinuities and handle occlusions. Our experiments using the Middlebury and MPI-Sintel optical flow datasets demonstrate the robustness and the efficiency of our proposed approach.

Keywords:

Laplace equations

Estimation

Optical imaging

Kernel

Eigenvalues and eigenfunctions

Optimization

Inverse problems

Optical flow

regularization

optimization

robust estimation

Graph Laplacian Regularization for Robust Optical Flow Estimation

Abstract

AI Summary

Journal

Organization