Spatio-Temporal Turbulence Mitigation: A Translational Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xingguang, Chimitt, Nicholas, Chi, Yiheng, Mao, Zhiyuan, Chan, Stanley H.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917632643432448
author Zhang, Xingguang
Chimitt, Nicholas
Chi, Yiheng
Mao, Zhiyuan
Chan, Stanley H.
author_facet Zhang, Xingguang
Chimitt, Nicholas
Chi, Yiheng
Mao, Zhiyuan
Chan, Stanley H.
contents Recovering images distorted by atmospheric turbulence is a challenging inverse problem due to the stochastic nature of turbulence. Although numerous turbulence mitigation (TM) algorithms have been proposed, their efficiency and generalization to real-world dynamic scenarios remain severely limited. Building upon the intuitions of classical TM algorithms, we present the Deep Atmospheric TUrbulence Mitigation network (DATUM). DATUM aims to overcome major challenges when transitioning from classical to deep learning approaches. By carefully integrating the merits of classical multi-frame TM methods into a deep network structure, we demonstrate that DATUM can efficiently perform long-range temporal aggregation using a recurrent fashion, while deformable attention and temporal-channel attention seamlessly facilitate pixel registration and lucky imaging. With additional supervision, tilt and blur degradation can be jointly mitigated. These inductive biases empower DATUM to significantly outperform existing methods while delivering a tenfold increase in processing speed. A large-scale training dataset, ATSyn, is presented as a co-invention to enable generalization in real turbulence. Our code and datasets are available at https://xg416.github.io/DATUM.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04244
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spatio-Temporal Turbulence Mitigation: A Translational Perspective
Zhang, Xingguang
Chimitt, Nicholas
Chi, Yiheng
Mao, Zhiyuan
Chan, Stanley H.
Image and Video Processing
Computer Vision and Pattern Recognition
Recovering images distorted by atmospheric turbulence is a challenging inverse problem due to the stochastic nature of turbulence. Although numerous turbulence mitigation (TM) algorithms have been proposed, their efficiency and generalization to real-world dynamic scenarios remain severely limited. Building upon the intuitions of classical TM algorithms, we present the Deep Atmospheric TUrbulence Mitigation network (DATUM). DATUM aims to overcome major challenges when transitioning from classical to deep learning approaches. By carefully integrating the merits of classical multi-frame TM methods into a deep network structure, we demonstrate that DATUM can efficiently perform long-range temporal aggregation using a recurrent fashion, while deformable attention and temporal-channel attention seamlessly facilitate pixel registration and lucky imaging. With additional supervision, tilt and blur degradation can be jointly mitigated. These inductive biases empower DATUM to significantly outperform existing methods while delivering a tenfold increase in processing speed. A large-scale training dataset, ATSyn, is presented as a co-invention to enable generalization in real turbulence. Our code and datasets are available at https://xg416.github.io/DATUM.
title Spatio-Temporal Turbulence Mitigation: A Translational Perspective
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.04244