26 June 2014 Efficient completion for corrupted low-rank images via alternating direction method
Author Affiliations +
J. of Electronic Imaging, 23(3), 033018 (2014). doi:10.1117/1.JEI.23.3.033018
We propose an efficient and easy-to-implement method to settle the inpainting problem for low-rank images following the recent studies about low-rank matrix completion. In general, our method has three steps: first, corresponding to the three channels of RGB color space, an incomplete image is split into three incomplete matrices; second, each matrix is restored by solving a convex problem derived from the nuclear norm relaxation; at last, the three recovered matrices are merged to produce the final output. During the process, in order to efficiently solve the nuclear norm minimization problem, we employ the alternating direction method. Except for the basic image inpainting problem, we also enable our method to handle cases where corrupted images not only have missing values but also have noisy entries. Our experiments show that our method outperforms the existing inpainting techniques both quantitatively and qualitatively. We also demonstrate that our method is capable of processing many other situations, including block-wise low-rank image completion, large-scale image restoration, and object removal.
© 2014 SPIE and IS&T
Wei Li, Lei Zhao, Duanqing Xu, Dongming Lu, "Efficient completion for corrupted low-rank images via alternating direction method," Journal of Electronic Imaging 23(3), 033018 (26 June 2014). https://doi.org/10.1117/1.JEI.23.3.033018

Image processing



Image restoration

Chemical elements

RGB color model

Mathematical modeling


A comparison of image inpainting techniques
Proceedings of SPIE (March 04 2015)
Block-Effect Reduction In Transform Coding
Proceedings of SPIE (November 20 1986)
Artistic halftoning: between technology and art
Proceedings of SPIE (December 21 1999)

Back to Top