Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations

TL;DR

The paper presents CoLIE, a neural implicit representation-based method for fast, high-quality low-light image enhancement that adapts well to diverse scenes and reduces computational costs.

Contribution

It introduces a novel implicit neural approach conditioned on local context for low-light enhancement, improving efficiency and adaptability over existing methods.

Findings

Outperforms existing methods in image quality and scene adaptability

Reduces computational overhead significantly

Enhances downstream low-light vision tasks

Abstract

Current deep learning-based low-light image enhancement methods often struggle with high-resolution images, and fail to meet the practical demands of visual perception across diverse and unseen scenarios. In this paper, we introduce a novel approach termed CoLIE, which redefines the enhancement process through mapping the 2D coordinates of an underexposed image to its illumination component, conditioned on local context. We propose a reconstruction of enhanced-light images within the HSV space utilizing an implicit neural function combined with an embedded guided filter, thereby significantly reducing computational overhead. Moreover, we introduce a single image-based training loss function to enhance the model's adaptability to various scenes, further enhancing its practical applicability. Through rigorous evaluations, we analyze the properties of our proposed framework, demonstrating its superiority in both image quality and scene adaptability. Furthermore, our evaluation extends to applications in downstream tasks within low-light scenarios, underscoring the practical utility of CoLIE. The source code is available at https://github.com/ctom2/colie.