Zero-shot restoration of back-lit images using deep internal learning

L Zhang, L Zhang, X Liu, Y Shen, S Zhang… - Proceedings of the 27th …, 2019 - dl.acm.org
How to restore back-lit images still remains a challenging task. State-of-the-art methods in
this field are based on supervised learning and thus they are usually restricted to specific …

Revisit Retinex Theory: Towards a Lightness‐Aware Restorer for Underexposed Images

L Zhang, A Zhu, Y Shen, S Zhao… - … Problems in Engineering, 2020 - Wiley Online Library
We investigate how to correct exposure of underexposed images. The bottleneck of previous
methods mainly lies in their naturalness and robustness when dealing with images with …

Towards automatic image exposure level assessment

L Zhang, X Yang, L Zhang, X Liu… - Mathematical …, 2020 - Wiley Online Library
The quality of acquired images can be surely reduced by improper exposures. Thus, in
many vision‐related industries, such as imaging sensor manufacturing and video …