DCT regularized extreme visual recovery

Publication Type:
Journal Article
IEEE Transactions on Image Processing, 2017, 26 (7), pp. 3360 - 3371
Issue Date:
Filename Description Size
07872479.pdfPublished Version4.26 MB
Adobe PDF
Full metadata record
© 2017 IEEE. Here we study the extreme visual recovery problem, in which over 90% of pixel values in a given image are missing. Existing low rank-based algorithms are only effective for recovering data with at most 90% missing values. Thus, we exploit visual data's smoothness property to help solve this challenging extreme visual recovery problem. Based on the discrete cosine transform (DCT), we propose a novel DCT regularizer that involves all pixels and produces smooth estimations in any view. Our theoretical analysis shows that the total variation regularizer, which only achieves local smoothness, is a special case of the proposed DCT regularizer. We also develop a new visual recovery algorithm by minimizing the DCT regularizer and nuclear norm to achieve a more visually pleasing estimation. Experimental results on a benchmark image data set demonstrate that the proposed approach is superior to the state-of-the-art methods in terms of peak signal-to-noise ratio and structural similarity.
Please use this identifier to cite or link to this item: