Structure-guided image completion via regularity statistics

Shuai Yang, Jiaying Liu, Sijie Song, Mading Li, Zongming Quo

Abstract

In this paper, we propose a novel hierarchical image completion approach using regularity statistics, considering structure features. Guided by dominant structures, the target image is used to generate reference images in a self-reproductive way by image data enhancement. The structure-guided image data enhancement allows us to expand the search space for samples. A Markov Random Field model is used to guide the enhanced image data combination to globally reconstruct the target image. For lower computational complexity and more accurate structure estimation, a hierarchical process is implemented. Experiments demonstrate the effectiveness of our method comparing to several state-of-the-art image completion techniques.
BibTeX
@inproceedings{yang2016structure,
  author = {Shuai Yang and Jiaying Liu and Sijie Song and Mading Li and Zongming Quo},
  title = {{Structure-guided image completion via regularity statistics}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2016},
  doi = {10.1109/icassp.2016.7471969},
}

Loading related content...

Figure