Extremely Low-light Image Enhancement with Scene Text Restoration
This addresses the challenge of enhancing extremely low-light images with a focus on text restoration, which is incremental as it builds on existing deep learning methods by adding specific components for text recovery.
The paper tackles the problem of insufficient detail recovery, particularly scene texts, in extremely low-light image enhancement by proposing a novel framework that restores texts and overall image quality simultaneously. The model outperforms state-of-the-art methods on See In the Dark and ICDAR15 datasets in image restoration, text detection, and text spotting.
Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved. However, we found out that most of these methods could not sufficiently recover the image details, for instance, the texts in the scene. In this paper, a novel image enhancement framework is proposed to precisely restore the scene texts, as well as the overall quality of the image simultaneously under extremely low-light images conditions. Mainly, we employed a self-regularised attention map, an edge map, and a novel text detection loss. In addition, leveraging synthetic low-light images is beneficial for image enhancement on the genuine ones in terms of text detection. The quantitative and qualitative experimental results have shown that the proposed model outperforms state-of-the-art methods in image restoration, text detection, and text spotting on See In the Dark and ICDAR15 datasets.