Quality Adaptive Low-Rank Based JPEG Decoding with Applications

TL;DR

This paper introduces a novel sparsity-based convex programming method that incorporates the non-linear DCT quantization mechanism to effectively remove compression noise and improve image restoration, especially for high-boosting tasks.

Contribution

It presents a new joint compression noise removal and image restoration approach that explicitly models DCT quantization, leading to enhanced restoration performance.

Findings

Significant performance improvements over existing methods

Effective noise removal in high-boosting image restoration tasks

Robustness to compression noise in practical applications

Abstract

Small compression noises, despite being transparent to human eyes, can adversely affect the results of many image restoration processes, if left unaccounted for. Especially, compression noises are highly detrimental to inverse operators of high-boosting (sharpening) nature, such as deblurring and superresolution against a convolution kernel. By incorporating the non-linear DCT quantization mechanism into the formulation for image restoration, we propose a new sparsity-based convex programming approach for joint compression noise removal and image restoration. Experimental results demonstrate significant performance gains of the new approach over existing image restoration methods.