CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task

TL;DR

CRNet is a unified neural network that effectively restores and enhances images by integrating multiple exposure inputs and explicitly processing high and low-frequency information, leading to superior visual quality.

Contribution

The paper introduces CRNet, a novel network architecture that combines multi-exposure inputs with frequency-aware modules for simultaneous image restoration and enhancement.

Findings

CRNet outperforms previous SOTA models in metrics and visual quality.

CRNet secured third place in the Bracketing Image Restoration and Enhancement Challenge.

The model effectively fuses multi-exposure information and enhances details through specialized modules.

Abstract

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality.