Atmospheric Turbulence Degraded Video with Recurrent GAN (ATVR-GAN)

Electrical Engineering Systems Seminar

Speaker: Bar Ettedgui

M.Sc. student under the supervision of Prof. Shai Avidan and Prof. Yitzhak Yitzhaky

Wednesday, 8^th May 2024, at 15:00

Room 011, Kitot Building, Faculty of Engineering

Atmospheric Turbulence Degraded Video with Recurrent GAN (ATVR-GAN)

Abstract

Atmospheric turbulence (AT) can change the path and direction of light during video capturing of a target in space due to the random motion of the turbulemient medium, a phenomenon that is most noticeable when shooting videos at long ranges, resulting in severe video dynamic distortion and blur. To mitigate geometric distortion and reduce spatially and temporally varying blur, we pro-pose a novel Atmospheric Turbulence Video Restoration Generative Adversarial Network (ATVR-GAN) with a specialized Recurrent Neural Network (RNN) generator, which is trained to predict the scene’s turbulent optical flow (OF) field and utilizes a recurrent structure to catch both spatial and temporal dependencies. The new architecture is trained using a newly combined loss function that counts for the spatiotemporal distortions, specifically tailored to the AT problem. Our network was tested on synthetic and real imaging data and compared against leading algorithms in the field of AT mitigation and image restoration. The proposed method outperformed these methods for both synthetic and real data examined.

השתתפות בסמינר תיתן קרדיט שמיעה = עפ"י רישום שם מלא + מספר ת.ז. בדף הנוכחות שיועבר באולם במהלך הסמינר