In this paper, we introduce and tackle the simultaneous enhancement and super-resolution (SESR) problem for underwater robot vision and provide an efficient solution for near real-time applications.
The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning.
The layer optimizes the unsharp masking parameters during model training, without any manual intervention.
#6 best model for Scene Text Detection on ICDAR 2013
Other contributions of this paper include a decomposition-and-fusion design of the enhancement network and the reinforcement-net for further contrast enhancement.
SOTA for Low-Light Image Enhancement on 3DMatch Benchmark (using extra training data)
Underwater images play a key role in ocean exploration, but often suffer from severe quality degradation due to light absorption and scattering in water medium.
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data?
We show that style generators outperform other GANs as well as Deep Image Prior as priors for image enhancement tasks.
In this paper we propose a novel deep learning framework to enhance underwater images by augmenting our network with wavelet corrected transformations.