Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition

TL;DR

This paper introduces HLNet, a novel image restoration and enhancement method that leverages high-low frequency decomposition to better handle various degradations, resulting in improved restoration quality.

Contribution

The paper proposes HLNet, which uses high-low frequency decomposition and specialized modules to address different image degradations more effectively than previous methods.

Findings

HLNet outperforms existing methods in image restoration quality.

High-low frequency decomposition improves handling of diverse degradations.

Shared and non-shared modules enhance feature extraction for restoration.

Abstract

In real-world scenarios, due to a series of image degradations, obtaining high-quality, clear content photos is challenging. While significant progress has been made in synthesizing high-quality images, previous methods for image restoration and enhancement often overlooked the characteristics of different degradations. They applied the same structure to address various types of degradation, resulting in less-than-ideal restoration outcomes. Inspired by the notion that high/low frequency information is applicable to different degradations, we introduce HLNet, a Bracketing Image Restoration and Enhancement method based on high-low frequency decomposition. Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules. In the shared weight modules, we use SCConv to extract common features from different degradations. In the non-shared weight modules, we introduce the High-Low Frequency Decomposition Block (HLFDB), which employs different methods to handle high-low frequency information, enabling the model to address different degradations more effectively. Compared to other networks, our method takes into account the characteristics of different degradations, thus achieving higher-quality image restoration.