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

Source: [Low-light Image Restoration with Short- and Long-exposure Raw Pairs](<https://www.sota2.com/research/paper/68fa69761e209131cea223cb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:00:47.140Z

Authors: Meng Chang, Huajun Feng, Zhihai Xu, Qi Li

Published: 2020-07-01T03:22:26.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Dual-Exposure Image Reconstruction on REDS-LL](<https://www.sota2.com/research/sota/dual-exposure-image-reconstruction-on-reds-ll.md>): Dual-Exposure Image Reconstruction; REDS-LL; Runtime (ms): 23.

- [Low-light image enhancement on REDS LL](<https://www.sota2.com/research/sota/low-light-image-enhancement-on-reds-ll.md>): Low-light Image Enhancement; REDS-LL; PSNR: 34.444.

- [Low-light image enhancement on PIED](<https://www.sota2.com/research/sota/low-light-image-enhancement-on-pied.md>): Low-light Image Enhancement; PIED; PSNR: 29.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.00199>)

[PDF](<https://arxiv.org/pdf/2007.00199.pdf>)