Extremely low-light image enhancement with scene text restoration
Document Type
Conference Item
Publication Date
1-1-2022
Abstract
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 conditions. Mainly, we employed a self-regularised attention map, an edge map, and a novel text detection loss. In addition, leveraging the 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.
Keywords
Low-light image, Enhancement, Scene text restoration
Divisions
ai
Publisher
IEEE
Publisher Location
345 E 47TH ST, NEW YORK, NY 10017 USA
Event Title
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Event Location
Montreal
Event Dates
21-25 August 2022
Event Type
conference