Learning to See in the Extremely Dark

TL;DR

This paper introduces a large-scale dataset and a diffusion-based method for enhancing RAW images captured in extremely dark environments, achieving better exposure and color restoration.

Contribution

It presents a novel paired dataset for extremely low-light RAW images and a diffusion model framework with specialized modules for improved enhancement.

Findings

Effective enhancement of extremely dark RAW images demonstrated

The dataset enables benchmarking of low-light RAW enhancement methods

The proposed method outperforms existing approaches on SIED and other benchmarks

Abstract

Learning-based methods have made promising advances in low-light RAW image enhancement, while their capability to extremely dark scenes where the environmental illuminance drops as low as 0.0001 lux remains to be explored due to the lack of corresponding datasets. To this end, we propose a paired-to-paired data synthesis pipeline capable of generating well-calibrated extremely low-light RAW images at three precise illuminance ranges of 0.01-0.1 lux, 0.001-0.01 lux, and 0.0001-0.001 lux, together with high-quality sRGB references to comprise a large-scale paired dataset named See-in-the-Extremely-Dark (SIED) to benchmark low-light RAW image enhancement approaches. Furthermore, we propose a diffusion-based framework that leverages the generative ability and intrinsic denoising property of diffusion models to restore visually pleasing results from extremely low-SNR RAW inputs, in which an Adaptive Illumination Correction Module (AICM) and a color consistency loss are introduced to ensure accurate exposure correction and color restoration. Extensive experiments on the proposed SIED and publicly available benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/JianghaiSCU/SIED.