Latent Disentanglement for Low Light Image Enhancement

TL;DR

This paper introduces LDE-Net, a novel low-light image enhancement network that uses latent disentanglement to separate content and illumination, improving enhancement quality and downstream task performance.

Contribution

The paper proposes a latent disentanglement framework with a Content-Aware Embedding module, advancing low-light image enhancement and downstream applications.

Findings

Outperforms state-of-the-art LLIE methods on benchmarks.

Effectively improves downstream tasks like UAV tracking and object detection.

Demonstrates the effectiveness of latent disentanglement in low-light vision.

Abstract

Many learning-based low-light image enhancement (LLIE) algorithms are based on the Retinex theory. However, the Retinex-based decomposition techniques in such models introduce corruptions which limit their enhancement performance. In this paper, we propose a Latent Disentangle-based Enhancement Network (LDE-Net) for low light vision tasks. The latent disentanglement module disentangles the input image in latent space such that no corruption remains in the disentangled Content and Illumination components. For LLIE task, we design a Content-Aware Embedding (CAE) module that utilizes Content features to direct the enhancement of the Illumination component. For downstream tasks (e.g. nighttime UAV tracking and low-light object detection), we develop an effective light-weight enhancer based on the latent disentanglement framework. Comprehensive quantitative and qualitative experiments demonstrate that our LDE-Net significantly outperforms state-of-the-art methods on various LLIE benchmarks. In addition, the great results obtained by applying our framework on the downstream tasks also demonstrate the usefulness of our latent disentanglement design.