LTT-GAN: Looking Through Turbulence by Inverting GANs
This addresses the challenge of face verification in turbulence-degraded images for surveillance or remote identification applications, representing an incremental advance in using GAN priors for this specific domain.
The paper tackles the problem of restoring face images degraded by atmospheric turbulence in long-range imaging by proposing LTT-GAN, a method that uses visual priors from a pre-trained GAN to preserve identity through a spatial periodic contextual distance and hierarchical pseudo connections. The result shows significant improvements over prior methods in visual quality and face verification accuracy.
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.