Low-light Image Restoration with Short- and Long-exposure Raw Pairs

TL;DR

This paper introduces a novel approach for low-light image restoration using paired short- and long-exposure raw images, employing a new data synthesis method and a fusion network to enhance image quality in challenging conditions.

Contribution

The paper presents a new data generation technique and a fusion network specifically designed for low-light image restoration, addressing noise, blur, and color distortion effectively.

Findings

Outperforms state-of-the-art methods in low-light image restoration

Successfully recovers scene details and colors in low-light conditions

Effectively reduces noise, motion blur, and color distortion

Abstract

Low-light imaging with handheld mobile devices is a challenging issue. Limited by the existing models and training data, most existing methods cannot be effectively applied in real scenarios. In this paper, we propose a new low-light image restoration method by using the complementary information of short- and long-exposure images. We first propose a novel data generation method to synthesize realistic short- and longexposure raw images by simulating the imaging pipeline in lowlight environment. Then, we design a new long-short-exposure fusion network (LSFNet) to deal with the problems of low-light image fusion, including high noise, motion blur, color distortion and misalignment. The proposed LSFNet takes pairs of shortand long-exposure raw images as input, and outputs a clear RGB image. Using our data generation method and the proposed LSFNet, we can recover the details and color of the original scene, and improve the low-light image quality effectively. Experiments demonstrate that our method can outperform the state-of-the art methods.