Back to Search
Start Over
Graph Laplacian Regularization for Robust Optical Flow Estimation.
- Source :
-
IEEE Transactions on Image Processing . 2020, Vol. 29, p3970-3983. 14p. - Publication Year :
- 2020
-
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. [ABSTRACT FROM AUTHOR]
- Subjects :
- *DENSE graphs
*OPTICAL flow
*INVERSE problems
*LAPLACIAN matrices
Subjects
Details
- Language :
- English
- ISSN :
- 10577149
- Volume :
- 29
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Image Processing
- Publication Type :
- Academic Journal
- Accession number :
- 170078086
- Full Text :
- https://doi.org/10.1109/TIP.2019.2945653