Burst Photography for Learning to Enhance Extremely Dark Images

TL;DR

This paper introduces a novel burst photography framework with a coarse-to-fine network architecture that enhances extremely dark raw images by reducing noise and recovering details, outperforming existing methods.

Contribution

It proposes a permutation invariant burst processing network that progressively enhances dark images, combining denoising and detail recovery in a unified architecture.

Findings

Produces sharper, more detailed images in low-light conditions

Outperforms state-of-the-art methods in perceptual quality

Effectively merges multiple low-light images for better results

Abstract

Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional enhancement techniques almost impossible to apply. Recently, learning-based approaches have shown very promising results for this task since they have substantially more expressive capabilities to allow for improved quality. Motivated by these studies, in this paper, we aim to leverage burst photography to boost the performance and obtain much sharper and more accurate RGB images from extremely dark raw images. The backbone of our proposed framework is a novel coarse-to-fine network architecture that generates high-quality outputs progressively. The coarse network predicts a low-resolution, denoised raw image, which is then fed to the fine network to recover fine-scale details and realistic textures. To further reduce the noise level and improve the color accuracy, we extend this network to a permutation invariant structure so that it takes a burst of low-light images as input and merges information from multiple images at the feature-level. Our experiments demonstrate that our approach leads to perceptually more pleasing results than the state-of-the-art methods by producing more detailed and considerably higher quality images.