You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement
Huiyuan Fu, Wenkai Zheng, Xiangyu Meng, Xin Wang, Chuanming Wang, Huadong Ma
Images captured in low-light conditions often suffer from significant quality degradation. Recent works have built a large variety of deep Retinex-based networks to enhance low-light images. The Retinex-based methods require decomposing the image into reflectance and illumination components, which is a highly ill-posed problem and there is no available ground truth. Previous works addressed this problem by imposing some additional priors or regularizers. However, finding an effective prior or regularizer that can be applied in various scenes is challenging, and the performance of the model suffers from too many additional constraints. We propose a contrastive learning method and a self-knowledge distillation method that allow training our Retinex-based model for Retinex decomposition without elaborate hand-crafted regularization functions. Rather than estimating reflectance and illuminance images and representing the final images as their element-wise products as in previous works, our regularizer-free Retinex decomposition and synthesis network (RFR) extracts reflectance and illuminance features and synthesizes them end-to-end. In addition, we propose a loss function for contrastive learning and a progressive learning strategy for self-knowledge distillation. Extensive experimental results demonstrate that our proposed methods can achieve superior performance compared with state-of-the-art approaches.
Discussion
-
https://fintechbase.icu/Simply desire to say your article is as astonishing. The clarity for your put up is just excellent and that i can suppose you're knowledgeable on this subject. Well with your permission allow me to snatch your feed to keep updated with coming near near post. Thank you a million and please continue the rewarding work.
Reply