LTT-GAN：通过反转GAN实现透过湍流观察
LTT-GAN: Looking Through Turbulence by Inverting GANs
AI总结：
提出LTT-GAN，利用GAN视觉先验和空间周期性上下文距离，结合分层伪连接，实现湍流退化图像的身份保持恢复，显著提升视觉质量与人脸验证精度。
摘要：
在许多远距离成像应用中，我们面临这样一种场景：捕获图像中出现的人往往受到大气湍流的退化影响。然而，由于这种退化导致图像几何变形和模糊，恢复此类退化图像以进行人脸验证十分困难。为了减轻湍流效应，本文提出了第一种利用训练良好的GAN所封装的视觉先验的湍流缓解方法。基于这些视觉先验，我们提出学习在空间周期性上下文距离上保持恢复图像的身份。这种距离可以在网络学习时考虑身份差异的同时，保持GAN恢复图像的真实感。此外，提出了分层伪连接，通过引入更多不改变身份的外观变化来促进身份保持学习。大量实验表明，我们的方法在恢复结果的视觉质量和人脸验证准确性方面均显著优于现有技术。
英文摘要：
In many applications of long-range imaging, we are faced with a scenario where a person appearing in the captured imagery is often degraded by atmospheric turbulence. However, restoring such degraded images for face verification is difficult since the degradation causes images to be geometrically distorted and blurry. To mitigate the turbulence effect, in this paper, we propose the first turbulence mitigation method that makes use of visual priors encapsulated by a well-trained GAN. Based on the visual priors, we propose to learn to preserve the identity of restored images on a spatial periodic contextual distance. Such a distance can keep the realism of restored images from the GAN while considering the identity difference at the network learning. In addition, hierarchical pseudo connections are proposed for facilitating the identity-preserving learning by introducing more appearance variance without identity changing. Extensive experiments show that our method significantly outperforms prior art in both the visual quality and face verification accuracy of restored results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
