LTT-GAN: Looking Through Turbulence by Inverting GANs

TL;DR

This paper introduces LTT-GAN, a novel turbulence mitigation method that leverages GAN-based visual priors to restore degraded long-range images, significantly improving face verification accuracy.

Contribution

It presents the first turbulence mitigation approach using GANs with identity-preserving spatial distance and hierarchical pseudo connections for enhanced restoration.

Findings

Outperforms prior methods in visual quality

Achieves higher face verification accuracy

Effectively preserves identity in restored images

Abstract

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.