Simultaneous Coding Artifact Reduction and Sharpness Enhancement

This paper presents an adaptive approach for simultaneous blocking artifact reduction and sharpness enhancement. The proposed method utilizes the local structure information to detect the blocking artifacts and the image edges. Then adaptive filtering is applied to remove the artifacts and sharpen the image detail. In order to obtain the optimal coefficients, we train the adaptive filters offline on a training set, which is composed by original images and the compressed blurred versions of those original images. Experimental results show that the proposed method has great effectiveness in both coding artifacts reduction and sharpness enhancement.