Low-Light Image Enhancement via a Deep Hybrid Network
Low-Light Image Enhancement via a Deep Hybrid Network
复制标题
通过深度混合网络进行低光图像增强
DOI：
10.1109/tip.2019.2910412
复制
发表时间：
2019-09-01
影响因子：
10.6
通讯作者：
Yang, Ming-Hsuan
中科院分区：
文献类型：
--
作者：
Ren, Wenqi;Liu, Sifei;Yang, Ming-Hsuan
相机传感器通常无法在光线不足的环境中捕获清晰的图像或视频。在本文中，我们提出了一种可训练的混合网络来增强此类退化图像的可见性。所提出的网络由两个不同的流组成，可以在统一网络中同时学习全局内容和清晰图像的显着结构。更具体地说，内容流通过编码器-解码器网络估计低光输入的全局内容。然而，内容流中的编码器往往会丢失一些结构细节。为了解决这个问题，我们提出了一种新颖的空间变异递归神经网络（RNN）作为边缘流，在另一个自动编码器的指导下对边缘细节进行建模。实验结果表明，所提出的网络与最先进的低光图像增强算法相比表现良好。
Camera sensors often fail to capture clear images or videos in a poorly lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the global content and the salient structures of the clear image in a unified network. More specifically, the content stream estimates the global content of the low-light input through an encoder–decoder network. However, the encoder in the content stream tends to lose some structure details. To remedy this, we propose a novel spatially variant recurrent neural network (RNN) as an edge stream to model edge details, with the guidance of another auto-encoder. The experimental results show that the proposed network favorably performs against the state-of-the-art low-light image enhancement algorithms.