Latent Disentanglement for Low Light Image Enhancement

Many learning-based low light image enhance- ment (LLIE) algorithms are based on the Retinex theory. However, the Retinex-based decomposition models introduce corruptions which limit their enhancement performance. In this paper, we propose a Latent Disentangle-based Enhance- ment 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 la- tent 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.