Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance

TL;DR

This paper introduces a geometric-aware framework that integrates depth priors into low-light image and video enhancement models, significantly improving their performance by leveraging scene structure information.

Contribution

The paper proposes a novel depth-guided enhancement framework with modules for depth-aware feature extraction and hierarchical feature fusion, enhancing existing LLE methods.

Findings

Significant improvement over baseline LLE methods on public benchmarks

Effective integration of depth priors enhances feature representation

Framework applicable to both images and videos

Abstract

Low-Light Enhancement (LLE) is aimed at improving the quality of photos/videos captured under low-light conditions. It is worth noting that most existing LLE methods do not take advantage of geometric modeling. We believe that incorporating geometric information can enhance LLE performance, as it provides insights into the physical structure of the scene that influences illumination conditions. To address this, we propose a Geometry-Guided Low-Light Enhancement Refine Framework (GG-LLERF) designed to assist low-light enhancement models in learning improved features for LLE by integrating geometric priors into the feature representation space. In this paper, we employ depth priors as the geometric representation. Our approach focuses on the integration of depth priors into various LLE frameworks using a unified methodology. This methodology comprises two key novel modules. First, a depth-aware feature extraction module is designed to inject depth priors into the image representation. Then, Hierarchical Depth-Guided Feature Fusion Module (HDGFFM) is formulated with a cross-domain attention mechanism, which combines depth-aware features with the original image features within the LLE model. We conducted extensive experiments on public low-light image and video enhancement benchmarks. The results illustrate that our designed framework significantly enhances existing LLE methods.