DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus

TL;DR

This paper introduces DAQE, a deep learning-based method that improves compressed image quality by exploiting defocus characteristics, enabling resource-efficient, region-specific enhancement of textures and defocus regions.

Contribution

The paper presents a novel defocus-aware deep learning architecture that adaptively enhances compressed images based on defocus levels and texture patterns, outperforming existing methods.

Findings

Significantly defocused regions have better compression quality.

Regions with different defocus levels exhibit diverse textures.

DAQE outperforms state-of-the-art methods in quality and resource efficiency.

Abstract

Image defocus is inherent in the physics of image formation caused by the optical aberration of lenses, providing plentiful information on image quality. Unfortunately, existing quality enhancement approaches for compressed images neglect the inherent characteristic of defocus, resulting in inferior performance. This paper finds that in compressed images, significantly defocused regions have better compression quality, and two regions with different defocus values possess diverse texture patterns. These observations motivate our defocus-aware quality enhancement (DAQE) approach. Specifically, we propose a novel dynamic region-based deep learning architecture of the DAQE approach, which considers the regionwise defocus difference of compressed images in two aspects. (1) The DAQE approach employs fewer computational resources to enhance the quality of significantly defocused regions and more resources to enhance the quality of other regions; (2) The DAQE approach learns to separately enhance diverse texture patterns for regions with different defocus values, such that texture-specific enhancement can be achieved. Extensive experiments validate the superiority of our DAQE approach over state-of-the-art approaches in terms of quality enhancement and resource savings.