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 the
generalization to real turbulence.
Video Results
Videos are from the BRIAR dataset, all subjects give the consent to show their images.
If videos are not played correctly, please consider to use Chrome or download them
