A method for recovering the underlying irradiance from a collection of images corrupted by atmospheric turbulence, by modeling the deformation using optical flow and a novel flow inversion algorithm, without requiring an explicit initialization of the reference template.
A novel framework, DeTurb, that combines geometric restoration using deformable 3D convolutions and feature enhancement with 3D Swin Transformers to effectively mitigate the effects of atmospheric turbulence in long-range imaging.