Variational Deep Atmospheric Turbulence Correction for Video

This paper presents a novel variational deep-learning approach for video atmospheric turbulence correction. We modify and tailor a Nonlinear Activation Free Network to video restoration. By including it in a variational inference framework, we boost the model's performance and stability. This i...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 3568 - 3572
Main Authors Lopez-Tapia, Santiago, Wang, Xijun, Katsaggelos, Aggelos K.
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Atmospheric modeling
atmospheric turbulence
deep learning
Degradation
Feature extraction
Nonlinear distortion
restoration
Robustness
Stability analysis
Video
Video sequences
Online AccessGet full text

Cover

More Information
Summary:This paper presents a novel variational deep-learning approach for video atmospheric turbulence correction. We modify and tailor a Nonlinear Activation Free Network to video restoration. By including it in a variational inference framework, we boost the model's performance and stability. This is achieved through conditioning the model on features extracted by a variational autoencoder (VAE). Furthermore, we enhance these features by making the encoder of the VAE include information pertinent to the image formation via a new loss based on the prediction of parameters of the geometrical distortion and the spatially variant blur responsible for the video sequence degradation. Experiments on a comprehensive synthetic video dataset demonstrate the effectiveness and reliability of the proposed method and validate its superiority compared to existing state-of-the-art approaches.
DOI:10.1109/ICIP49359.2023.10222374