Yang Wenhan, Wang Shiqi, Fang Yuming, Wang Yue, Liu Jiaying
IEEE Trans Image Process. 2021;30:3461-3473. doi: 10.1109/TIP.2021.3062184. Epub 2021 Mar 9.
It has been widely acknowledged that under-exposure causes a variety of visual quality degradation because of intensive noise, decreased visibility, biased color, etc. To alleviate these issues, a novel semi-supervised learning approach is proposed in this paper for low-light image enhancement. More specifically, we propose a deep recursive band network (DRBN) to recover a linear band representation of an enhanced normal-light image based on the guidance of the paired low/normal-light images. Such design philosophy enables the principled network to generate a quality improved one by reconstructing the given bands based upon another learnable linear transformation which is perceptually driven by an image quality assessment neural network. On one hand, the proposed network is delicately developed to obtain a variety of coarse-to-fine band representations, of which the estimations benefit each other in a recursive process mutually. On the other hand, the extracted band representation of the enhanced image in the recursive band learning stage of DRBN is capable of bridging the gap between the restoration knowledge of paired data and the perceptual quality preference to high-quality images. Subsequently, the band recomposition learns to recompose the band representation towards fitting perceptual regularization of high-quality images with the perceptual guidance. The proposed architecture can be flexibly trained with both paired and unpaired data. Extensive experiments demonstrate that our method produces better enhanced results with visually pleasing contrast and color distributions, as well as well-restored structural details.
人们普遍认为，曝光不足会导致各种视觉质量下降，如噪声密集、能见度降低、颜色偏差等。为了缓解这些问题，本文提出了一种新颖的半监督学习方法用于低光图像增强。具体而言，我们提出了一种深度递归带网络（DRBN），以基于配对的低光/正常光图像的指导来恢复增强后的正常光图像的线性带表示。这种设计理念使该有原则的网络能够通过基于另一个由图像质量评估神经网络感知驱动的可学习线性变换来重建给定的带，从而生成质量更高的图像。一方面，所提出的网络经过精心设计，以获得各种从粗到细的带表示，其中的估计在递归过程中相互受益。另一方面，在DRBN的递归带学习阶段提取的增强图像的带表示能够弥合配对数据的恢复知识与对高质量图像的感知质量偏好之间的差距。随后，带重新组合学习在感知指导下将带表示重新组合，以适应高质量图像的感知正则化。所提出的架构可以使用配对和未配对数据进行灵活训练。大量实验表明，我们的方法产生了更好的增强结果，具有视觉上令人愉悦的对比度和颜色分布，以及恢复良好的结构细节。
