Nonlocal Sparse and Low-Rank Regularization for Optical Flow Estimation
Authors:
- 27 August 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (10) , 4527-4538
Abstract
Designing an appropriate regularizer is of great importance for accurate optical flow estimation. Recent works exploiting the nonlocal similarity and the sparsity of the motion field have led to promising flow estimation results. In this paper, we propose to unify these two powerful priors. To this end, we propose an effective flow regularization technique based on joint low-rank and sparse matrix recovery. By grouping similar flow patches into clusters, we effectively regularize the motion field by decomposing each set of similar flow patches into a low-rank component and a sparse component. For better enforcing the low-rank property, instead of using the convex nuclear norm, we use the log det (·) function as the surrogate of rank, which can also be efficiently minimized by iterative singular value thresholding. Experimental results on the Middlebury benchmark show that the performance of the proposed nonlocal sparse and low-rank regularization method is higher than (or comparable to) those of previous approaches that harness these same priors, and is competitive to current state-of-the-art methods.Keywords
Funding Information
- Major State Basic Research Development Program of China (973 Program) (2013CB329402)
- Natural Science Foundation of China (61227004, 61471281, 61390512, 61100154)
- Program for New Scientific and Technological Star of Shaanxi Province (2014KJXX-46)
- Fundamental Research Funds of the Central Universities of China (BDY081424)
- Open Project of Beijing Multimedia and Intelligent Software Key Laboratory, Beijing University of Technology, Beijing, China
This publication has 26 references indexed in Scilit:
- Optical flow estimation using learned sparse model2011
- Sparsity-based image denoising via dictionary learning and structural clustering2011
- Robust principal component analysis?Journal of the ACM, 2011
- A Database and Evaluation Methodology for Optical FlowInternational Journal of Computer Vision, 2010
- Sparsity model for robust optical flow estimation at motion discontinuities2010
- Motion estimation with non-local total variation regularization2010
- Matrix Completion With NoiseProceedings of the IEEE, 2010
- Non-local sparse models for image restoration2009
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- Multiscale Minimization of Global Energy Functions in Some Visual Recovery ProblemsCVGIP: Image Understanding, 1994