Exposure Bracketing Is All You Need For A High-Quality Image

TL;DR

This paper introduces a novel approach using exposure bracketing and a temporally modulated recurrent network to enhance low-light image quality by combining multiple images, with a focus on synthetic pre-training and real-world adaptation.

Contribution

It proposes a new method leveraging exposure bracketing with a TMRNet and self-supervised adaptation, addressing the challenge of real-world data collection.

Findings

Outperforms state-of-the-art multi-image processing methods

Effective in real-world nighttime scenarios

Demonstrates the benefit of synthetic pre-training and adaptation

Abstract

It is highly desired but challenging to acquire high-quality photos with clear content in low-light environments. Although multi-image processing methods (using burst, dual-exposure, or multi-exposure images) have made significant progress in addressing this issue, they typically focus on specific restoration or enhancement problems, and do not fully explore the potential of utilizing multiple images. Motivated by the fact that multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution, we propose to utilize exposure bracketing photography to get a high-quality image by combining these tasks in this work. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data and then adapts it to real-world unlabeled images. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed. Moreover, we construct a data simulation pipeline to synthesize pairs and collect real-world images from 200 nighttime scenarios. Experiments on both datasets show that our method performs favorably against the state-of-the-art multi-image processing ones. Code and datasets are available at https://github.com/cszhilu1998/BracketIRE.