当前位置: X-MOL 学术Math. Probl. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Revisit Retinex Theory: Towards a Lightness-Aware Restorer for Underexposed Images
Mathematical Problems in Engineering Pub Date : 2020-07-02 , DOI: 10.1155/2020/1325705
Lin Zhang 1 , Anqi Zhu 1 , Ying Shen 1 , Shengjie Zhao 1 , Huijuan Zhang 1
Affiliation  

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 various exposure levels. When facing well-exposed or extremely underexposed images, they may produce over- or underenhanced outputs. In this paper, we propose a novel retinex-based approach, namely, LiAR (short for lightness-aware restorer). The word “lightness-aware” refers to that the estimated illumination not only is a component to be adjusted but also serves as a measure that reflects the brightness of the scene, determining the degree of adjustment. In this way, underexposed images can be restored adaptively according to their own brightness. Given an image, LiAR first estimates its illumination map using a specially designed loss function which can ensure the result’s color consistency and texture richness. Then adaptive correction is performed to get properly exposed output. LiAR is based on internal optimization of the single test image and does not need any prior training, implying that it can adapt itself to different settings per image. Additionally, LiAR can be easily extended to the video case due to its simplicity and stability. Experiments demonstrate that facing images/videos with various exposure levels, LiAR can achieve robust and real-time correction with high contrast and naturalness. The relevant code and collected data are publicly available at https://cslinzhang.github.io/LiAR-Homepage/.

中文翻译:

回顾Retinex理论:面向曝光不足图像的亮度感知恢复器

我们研究如何校正曝光不足图像的曝光。以前方法的瓶颈主要在于处理各种曝光水平的图像时的自然性和鲁棒性。当面对曝光良好或曝光过度的图像时,它们可能会产生过度或增强的输出。在本文中,我们提出了一种新颖的基于retinex的方法,即LiAR(明度感知还原器的缩写)。词语“感知亮度”是指估计的照明度不仅是要调节的成分,而且还用作反映场景的亮度,确定调节程度的量度。这样,曝光不足的图像可以根据其自身的亮度进行自适应恢复。给定一张图片,LiAR首先使用专门设计的损失函数来估计其照明图,该函数可以确保结果的颜色一致性和纹理丰富度。然后执行自适应校正以获得正确曝光的输出。LiAR基于单个测试图像的内部优化,不需要任何事先培训,这意味着它可以适应每个图像的不同设置。另外,由于其简单性和稳定性,LiAR可以轻松扩展到视频盒。实验表明,面对具有不同曝光水平的图像/视频,LiAR可以实现具有高对比度和自然度的强大且实时的校正。有关代码和收集的数据可在https://cslinzhang.github.io/LiAR-Homepage/上公开获得。然后执行自适应校正以获得正确曝光的输出。LiAR基于单个测试图像的内部优化,不需要任何事先培训,这意味着它可以适应每个图像的不同设置。另外,由于其简单性和稳定性,LiAR可以轻松扩展到视频盒。实验表明,面对各种曝光水平的图像/视频,LiAR可以实现具有高对比度和自然度的强大且实时的校正。有关代码和收集的数据可在https://cslinzhang.github.io/LiAR-Homepage/上公开获得。然后执行自适应校正以获得正确曝光的输出。LiAR基于单个测试图像的内部优化,不需要任何事先培训,这意味着它可以适应每个图像的不同设置。另外,由于其简单性和稳定性,LiAR可以轻松扩展到视频盒。实验表明,面对具有不同曝光水平的图像/视频,LiAR可以实现具有高对比度和自然度的强大且实时的校正。有关代码和收集的数据可在https://cslinzhang.github.io/LiAR-Homepage/上公开获得。LiAR的简单性和稳定性使其可以轻松扩展到视频盒。实验表明,面对各种曝光水平的图像/视频,LiAR可以实现具有高对比度和自然度的强大且实时的校正。有关代码和收集的数据可在https://cslinzhang.github.io/LiAR-Homepage/上公开获得。LiAR的简单性和稳定性使其可以轻松扩展到视频盒。实验表明,面对各种曝光水平的图像/视频,LiAR可以实现具有高对比度和自然度的强大且实时的校正。有关代码和收集的数据可在https://cslinzhang.github.io/LiAR-Homepage/上公开获得。
更新日期:2020-07-02
down
wechat
bug