Image Recovery based on Local and Nonlocal Regularizations
Recently, a nonlocal low-rank regularization based compressive sensing approach (NLR) which exploits structured sparsity of similar patches has shown the state-of-the-art performance in image recovery. However, NLR cannot efficiently preserve local structures because it ignores the relationship between pixels. In addition, the surrogate logdet function used in NLR cannot well approximate the rank. In this paper, a novel approach based on local and nonlocal regularizations toward exploiting the sparse-gradient property and nonlocal low-rank property (SGLR) has been proposed. Weighted schatten-p norm and lq norm have been used as better non-convex surrogate functions for the rank and l0 norm. In addition, an efficient iterative algorithm is developed to solve the resulting recovery problem. The experimental results have demonstrated that SGLR outperforms existing state-of-the-art CS algorithms.
KeywordsCompressive sensing Nonlocal low-rank regularization Total variation Weighted schatten-p norm Alternating direction methods of multipliers
This work was supported by the Natural Science Fund for Colleges and Universities in Jiangsu Province (Grant No. 16KJB520014), the Doctor Initial Captional of Jinling Institute of Technology Nanjing (No. jit-b-201508), the Scientific Research Starting Foundation of Jinling Institute of Technology for Introducing Talents (No. jit-rcyj-201505), and sponsored by the Jiangsu Key Laboratory of Image and Video Understanding for Social Safety (Nanjing University of Science and Technology) (Grant No. 30916014107).
- 9.Egiazarian K, Foi A, Katkovnik V (2007) Compressed sensing image reconstruction via recursive spatially adaptive filtering. IEEE International Conference on Image Processing, San Antonio, TX, USA 1:549–552Google Scholar
- 10.Fazel M, Hindi H, Boyd SP (2003) Log-det heuristic for matrix rank minimization with applications to Hankel and Euclidean distance matrices, vol 3. IEEE American Control Conference, Denver, pp 2156–2162Google Scholar
- 13.Li W, Wang P, Qiao H (2010) Double Least Squares Pursuit for Sparse Decomposition. International Conference on Intelligent Information Processing, Berlin, Heidelberg, pp 357–363Google Scholar
- 15.Mohan K, Fazel M (2010) Reweighted nuclear norm minimization with application to system identification. IEEE American Control Conference, Baltimore, pp 2953–2959Google Scholar
- 16.Nie F, Huang H, Ding C (2012) Low-rank matrix recovery via efficient schatten p-norm minimization. Twenty-Sixth AAAI Conference on Artificial Intelligence, Toronto, pp 655–661Google Scholar
- 18.Shu X, Yang J, Ahuja N (2014) Non-local compressive sampling recovery. IEEE International Conference on Computational Photography (ICCP), Santa Clara, pp 1–8Google Scholar
- 19.Shu X, Ahuja N (2010) Hybrid Compressive Sampling via a New Total Variation TVL1. European Conference on Computer Vision, Santa Clara, pp 393–404Google Scholar
- 21.Xie Y, Qu Y, Tao D, Wu W, Yuan Q, Zhang W (2016) Hyperspectral Image Restoration via Iteratively Regularized Weighted Schatten p-Norm Minimization. IEEE Trans Geosci Remote Sens 54(8):4642–4659Google Scholar
- 22.Xie Y, Gu S, Liu Y, Zuo W, Zhang W, Zhang L (2015) Weighted schatten, p-norm minimization for image denoising and background subtraction. IEEE Trans Image Process 25(10):4842–4857Google Scholar
- 24.Zhang J, Zhao D, Zhao C (2012) Compressed sensing recovery via collaborative sparsity. IEEE Data Compression Conference, Snowbird, pp 287–296Google Scholar
- 25.Zhang J, Liu S, Xiong R, Ma S, Zhao D (2013) Improved total variation based image compressive sensing recovery by nonlocal regularization. IEEE International Symposium on Circuits and Systems, Beijing, pp 2836–2839Google Scholar
- 29.Zhao C, Zhang J, Ma S, Gao W (2016) Nonconvex Lp Nuclear Norm based ADMM Framework for Compressed Sensing. IEEE Data Compression Conference (DCC2016), Snowbird, pp 161–170Google Scholar