Aiming at the problems of narrow dynamic range, serious noise and color deviation in dark light images, a dark light image enhancement network based on supervised learning is proposed. The enhancement process is divided into three steps: layer decomposition, reflection recovery, and illumination adjustment. Combined with Retinex theory, three-layer Unet++ is designed to decompose the image into reflection component and illumination component. The reflection recovery firstly combines the light-guided attention mask to assign new weights to the reflection components, and then sends them to the full-scale U-shaped network for image denoising and detail restoration. Illumination adjustment adjusts the illumination adaptively. This paper is validated on several datasets with improved subjective and objective evaluation results, which can effectively suppress noise and distortion problems, and significantly improve image brightness and quality.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.