Low Dimensional Manifold Regularization Based Blind Image Inpainting and Non-Uniform Impulse Noise Recovery

Mei Gao, Baosheng Kang, Xiangchu Feng, Lixia Cao, Wenjuan ZhangIEEE Access 2020 · OpenReview

Abstract

Blind image inpainting is a challenging task in image processing. Motivated by the excellent performance of low dimensional manifold model (LDMM) in image inpainting for large-scale pixels missing, we introduce a novel blind inpainting model to repair images with missing pixels or damaged with impulse noise, in spite of the unknown locations of the corrupted pixels. We applied logarithmic transformation to separate the image and binary mask. LDMM regularization and l <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> norm regularization were applied respectively to simultaneously estimate the image and the mask. The resulted minimization problem was then solved by the split Bregman algorithm. The simulation results showed that the proposed model, compared with the existing ones, can effectively restore the image with large uniform and non-uniform missing rate.
BibTeX
@inproceedings{gao2020low,
  author = {Mei Gao and Baosheng Kang and Xiangchu Feng and Lixia Cao and Wenjuan Zhang},
  title = {{Low Dimensional Manifold Regularization Based Blind Image Inpainting and Non-Uniform Impulse Noise Recovery}},
  booktitle = {IEEE Access},
  year = {2020},
  url = {https://openreview.net/forum?id=ppruyO7eyrx},
}

Loading related content...

Figure