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

TL;DR

This work addresses the challenge of producing high-quality images in low-light conditions by exploiting exposure bracketing to jointly perform denoising, deblurring, HDR reconstruction, and SR. It introduces BracketIRE, which pretrains on synthetic paired data and then adapts to real-world unlabeled images using a temporally modulated recurrent network (TMRNet) and self-supervised adaptation. The key contributions are the data simulation pipeline for synthetic paired data, the TMRNet architecture with frame-specific aggregation, and the self-supervised adaptation strategy that leverages temporal cues to bridge the synthetic-real gap. Experiments on synthetic and real-world night datasets show state-of-the-art performance against multi-image baselines, with improved artifact suppression and detail retention, highlighting practical potential for night HDR imaging on mobile devices.

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.

Figures (14)

• Figure 1: Illustration of baseline recurrent network (e.g., RBSR wu2023rbsr) and our TMRNet. Instead of sharing parameters of aggregation module $\mathcal{A}$ for all frames, we divide it into a common one $\mathcal{A}^c$ for all frames and a specific one $\mathcal{A}^s_i$ only for $i$-th frame. Modules with different colors have different parameters.
• Figure 2: Self-supervised loss terms for real-image adaptation. $\mathcal{B}$ denotes TMRNet for BracketIRE or BracketIRE+ task. In sub-figure (a), an integer from $1$ to $R$$(R<T)$ is randomly chosen as $r$. In sub-figure (b), EMA denotes exponential moving average.
• Figure 3: Visual comparison on the synthetic dataset of BracketIRE task. Our method restores sharper edges and clearer details.
• Figure 3: Effect of number of input multi-exposure frames.
• Figure 4: Visual comparison on the real-world dataset of BracketIRE task. Note that there is no ground-truth. Our results have fewer ghosting artifacts.