Graph Laplacian Regularization for Robust Optical Flow Estimation

Sean I. Young, Aous Thabit Naman, David TaubmanIEEE TIP 2020 · OpenReview

Abstract

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.
BibTeX
@article{young2020graph,
  author = {Sean I. Young and Aous Thabit Naman and David Taubman},
  title = {{Graph Laplacian Regularization for Robust Optical Flow Estimation}},
  journal = {IEEE Trans. Image Process.},
  year = {2020},
  url = {https://openreview.net/forum?id=MTAtJQFewUN},
}

Loading related content...

Figure