Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition

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.

1. Introduction

In real-world scenarios, the presence of various image degradations makes it challenging to capture high-quality, clear content photos. Low exposure can lead to increased noise, especially in dark areas, potentially causing loss of detail. Similarly, bright areas in high-exposure images may lose detail due to overexposure. Despite numerous single-image restoration methods proposed, such as denoising[1], [5], [17], [28], [51], [53], deblurring[7], [32], [36], [40], [51], super-resolution[10], [26], [29] and high dynamic range image reconstruction[15], [25], their performance is constrained by the insufficient information present in single images.