Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images

TL;DR

This paper introduces a resource-efficient blind quality enhancement method for compressed images that adaptively enhances image quality using a dynamic neural network with an early-exit strategy, improving efficiency and effectiveness.

Contribution

It proposes a novel adaptive deep neural network with early-exit for blind quality enhancement, reducing resource consumption and handling images of unknown quality.

Findings

Achieves state-of-the-art blind quality enhancement performance.

Reduces computational resources compared to traditional methods.

Effectively handles images with varying levels of compression artifacts.

Abstract

Lossy image compression is pervasively conducted to save communication bandwidth, resulting in undesirable compression artifacts. Recently, extensive approaches have been proposed to reduce image compression artifacts at the decoder side; however, they require a series of architecture-identical models to process images with different quality, which are inefficient and resource-consuming. Besides, it is common in practice that compressed images are with unknown quality and it is intractable for existing approaches to select a suitable model for blind quality enhancement. In this paper, we propose a resource-efficient blind quality enhancement (RBQE) approach for compressed images. Specifically, our approach blindly and progressively enhances the quality of compressed images through a dynamic deep neural network (DNN), in which an early-exit strategy is embedded. Then, our approach can automatically decide to terminate or continue enhancement according to the assessed quality of enhanced images. Consequently, slight artifacts can be removed in a simpler and faster process, while the severe artifacts can be further removed in a more elaborate process. Extensive experiments demonstrate that our RBQE approach achieves state-of-the-art performance in terms of both blind quality enhancement and resource efficiency. The code is available at https://github.com/RyanXingQL/RBQE.