ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence

TL;DR

This paper introduces ATFaceGAN, a novel generative model that restores and recognizes faces from images degraded by atmospheric turbulence by disentangling blur and deformation effects.

Contribution

The paper presents a new single-frame face restoration method that separates turbulence effects into blur and deformation components for improved image quality.

Findings

Effective turbulence disentanglement and restoration demonstrated.

Improved face recognition accuracy on degraded images.

Generates sharp, detailed face images from turbulent conditions.

Abstract

Image degradation due to atmospheric turbulence is common while capturing images at long ranges. To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image. The disentanglement is achieved by decomposing the distortion due to turbulence into blur and deformation components using deblur generator and deformation correction generator respectively. Two paths of restoration are implemented to regularize the disentanglement and generate two restored images from one degraded image. A fusion function combines the features of the restored images to reconstruct a sharp image with rich details. Adversarial and perceptual losses are added to reconstruct a sharp image and suppress the artifacts respectively. Extensive experiments demonstrate the effectiveness of the proposed restoration algorithm, which achieves satisfactory performance in face restoration and face recognition.