Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
This work addresses the issue of color deviation and unnatural textures in low-light image enhancement for computer vision applications, representing an incremental improvement by incorporating semantic guidance into existing methods.
The paper tackles the problem of low-light image enhancement by addressing the lack of semantic information in existing methods, proposing a semantic-aware knowledge-guided framework (SKF) that integrates semantic priors to improve color consistency and texture, resulting in models equipped with SKF significantly outperforming baselines on multiple datasets.
Low-light image enhancement (LLIE) investigates how to improve illumination and produce normal-light images. The majority of existing methods improve low-light images via a global and uniform manner, without taking into account the semantic information of different regions. Without semantic priors, a network may easily deviate from a region's original color. To address this issue, we propose a novel semantic-aware knowledge-guided framework (SKF) that can assist a low-light enhancement model in learning rich and diverse priors encapsulated in a semantic segmentation model. We concentrate on incorporating semantic knowledge from three key aspects: a semantic-aware embedding module that wisely integrates semantic priors in feature representation space, a semantic-guided color histogram loss that preserves color consistency of various instances, and a semantic-guided adversarial loss that produces more natural textures by semantic priors. Our SKF is appealing in acting as a general framework in LLIE task. Extensive experiments show that models equipped with the SKF significantly outperform the baselines on multiple datasets and our SKF generalizes to different models and scenes well. The code is available at Semantic-Aware-Low-Light-Image-Enhancement.