Exploiting sparsity in dense optical flow

Abstract

In this paper we validated that the dense optical flow field is sparse in certain frequency domains, while the flow gradient field is also sparse in image domain. Based on this sparsity prior, the optical flow estimation problem is casted as sparse signal recovery from highly shorted measurements. By minimizing its l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm in frequency domain and gradient domain, the model can accurately estimate the dense flow field without other assumptions. Outliers are further identified and removed in the flow denoising process to improve the results. Experiments show that our method significantly outperforms traditional methods based on global or piecewise smoothness priors. Moreover, it can well handle the complexity incurred by motion discontinuities.