ATFaceGAN : Single Face Image Restoration and Recognition from Atmospheric Turbulence
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Detail(s)
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020 |
| Editors | Vitomir Štruc, Francisco Gómez-Fernández |
| Publisher | Institute of Electrical and Electronics Engineers, Inc. |
| Pages | 32-39 |
| ISBN (electronic) | 978-1-7281-3079-8 |
| ISBN (print) | 978-1-7281-3080-4 |
| Publication status | Published - Nov 2020 |
| Externally published | Yes |
Publication series
| Name | Proceedings - IEEE International Conference on Automatic Face and Gesture Recognition, FG |
|---|
Conference
| Title | 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) |
|---|---|
| Place | Argentina |
| City | Buenos Aires |
| Period | 16 - 20 November 2020 |
Link(s)
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. © 2020 IEEE.
Research Area(s)
- Face Recognition, Face Verification, Generative Adversarial Networks, Image Restoration, Turbulence Mitigation
Citation Format(s)
Proceedings - 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020. ed. / Vitomir Štruc; Francisco Gómez-Fernández. Institute of Electrical and Electronics Engineers, Inc., 2020. p. 32-39 (Proceedings - IEEE International Conference on Automatic Face and Gesture Recognition, FG).
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
