Group-based truncated l1-2 model for image inpainting

Tian-Hui Ma, Yifei Lou, Ting-Zhu Huang, Xi-Le Zhao

Abstract

We propose a novel image inpainting model that can effectively estimate missing pixels in an observed image. The latent image is characterized by a group-based low-rank prior, which assumes that a group of vectorized similar image patches can be well approximated by a low-rank matrix. We enforce the low-rankness of each group by penalizing a truncated difference of the l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> and the l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> norms of its singular values, which achieves a close approximation to the matrix rank. We apply a difference of convex algorithm (DCA) to solve the proposed model efficiently. Our method is validated on filling missing blocks and randomly missing pixels, with superior performance over the state-of-the-art.
BibTeX
@inproceedings{ma2017group,
  author = {Tian-Hui Ma and Yifei Lou and Ting-Zhu Huang and Xi-Le Zhao},
  title = {{Group-based truncated l1-2 model for image inpainting}},
  booktitle = {ICIP},
  year = {2017},
  doi = {10.1109/icip.2017.8296648},
}

Loading related content...

Figure