Low-Light Image Enhancement via Structure Modeling and Guidance

TL;DR

This paper introduces a novel low-light image enhancement framework that combines structure modeling via edge detection with appearance enhancement, resulting in sharper, more realistic images and state-of-the-art performance across multiple datasets.

Contribution

It proposes a structure-guided enhancement framework using a modified generative model and a novel enhancement module, trained end-to-end for improved low-light image quality.

Findings

Achieves state-of-the-art performance on sRGB and RAW datasets.

Robust edge detection in dark, noisy regions.

Effective end-to-end training of structure and appearance models.

Abstract

This paper proposes a new framework for low-light image enhancement by simultaneously conducting the appearance as well as structure modeling. It employs the structural feature to guide the appearance enhancement, leading to sharp and realistic results. The structure modeling in our framework is implemented as the edge detection in low-light images. It is achieved with a modified generative model via designing a structure-aware feature extractor and generator. The detected edge maps can accurately emphasize the essential structural information, and the edge prediction is robust towards the noises in dark areas. Moreover, to improve the appearance modeling, which is implemented with a simple U-Net, a novel structure-guided enhancement module is proposed with structure-guided feature synthesis layers. The appearance modeling, edge detector, and enhancement module can be trained end-to-end. The experiments are conducted on representative datasets (sRGB and RAW domains), showing that our model consistently achieves SOTA performance on all datasets with the same architecture.