Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform

Zhiyuan Mao, Nicholas Chimitt, Stanley H. Chan; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 14759-14768

Abstract

Fast and accurate simulation of imaging through atmospheric turbulence is essential for developing turbulence mitigation algorithms. Recognizing the limitations of previous approaches, we introduce a new concept known as the phase-to-space (P2S) transform to significantly speed up the simulation. P2S is built upon three ideas: (1) reformulating the spatially varying convolution as a set of invariant convolutions with basis functions, (2) learning the basis function via the known turbulence statistics models, (3) implementing the P2S transform via a light-weight network that directly converts the phase representation to spatial representation. The new simulator offers 300x - 1000x speed up compared to the mainstream split-step simulators while preserving the essential turbulence statistics.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Mao_2021_ICCV, author = {Mao, Zhiyuan and Chimitt, Nicholas and Chan, Stanley H.}, title = {Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {14759-14768} }