Paper
10 October 2023 Full-scale feature fusion dark-light image enhancement network
Tingting Huang, Shangyou Zeng
Author Affiliations +
Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 127995L (2023) https://doi.org/10.1117/12.3005878
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia
Abstract
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.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Tingting Huang and Shangyou Zeng "Full-scale feature fusion dark-light image enhancement network", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 127995L (10 October 2023); https://doi.org/10.1117/12.3005878
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Light sources and illumination

Image enhancement

Reflection

Feature fusion

Image processing

Color

Image restoration

Back to Top