Atmospheric Turbulence Correction via Variational Deep Diffusion
This work addresses image restoration for applications like surveillance or astronomy, but it appears incremental as it applies a known method (diffusion models) to a specific domain problem.
The paper tackled the problem of correcting atmospheric turbulence distortions in images, which involve geometric distortion and spatially variant blur, by proposing a novel deep conditional diffusion model under a variational inference framework, achieving good quantitative and qualitative results on a synthetic dataset.
Atmospheric Turbulence (AT) correction is a challenging restoration task as it consists of two distortions: geometric distortion and spatially variant blur. Diffusion models have shown impressive accomplishments in photo-realistic image synthesis and beyond. In this paper, we propose a novel deep conditional diffusion model under a variational inference framework to solve the AT correction problem. We use this framework to improve performance by learning latent prior information from the input and degradation processes. We use the learned information to further condition the diffusion model. Experiments are conducted in a comprehensive synthetic AT dataset. We show that the proposed framework achieves good quantitative and qualitative results.