Cross-frequency spectral prediction for compressed image restoration

We propose a cross-domain correlation in compress images, and introduce a novel spectral prediction algorithm to restore lossy spectral information caused by compression. This cross-frequency spectral predication algorithm is inspired from the spatial correlation and the connection between discrete cosine transform and Hadamard transform. The relationship among cross-frequency coefficients is adopted to predict spectral coefficients. We apply the spectral prediction algorithm in compressed image restoration under the total variation (TV) based regularization. Experimental results of restoration with or without cross-frequency spectral predication are compared, remarkable improvement is observed from the results with cross-frequency spectral prediction.