Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model

07/20/2022
by   Zhiyuan Mao, et al.
0

Image restoration algorithms for atmospheric turbulence are known to be much more challenging to design than traditional ones such as blur or noise because the distortion caused by the turbulence is an entanglement of spatially varying blur, geometric distortion, and sensor noise. Existing CNN-based restoration methods built upon convolutional kernels with static weights are insufficient to handle the spatially dynamical atmospheric turbulence effect. To address this problem, in this paper, we propose a physics-inspired transformer model for imaging through atmospheric turbulence. The proposed network utilizes the power of transformer blocks to jointly extract a dynamical turbulence distortion map and restore a turbulence-free image. In addition, recognizing the lack of a comprehensive dataset, we collect and present two new real-world turbulence datasets that allow for evaluation with both classical objective metrics (e.g., PSNR and SSIM) and a new task-driven metric using text recognition accuracy. Both real testing sets and all related code will be made publicly available.

READ FULL TEXT

page 9

page 12

page 13

page 14

research
07/13/2022

Imaging through the Atmosphere using Turbulence Mitigation Transformer

Restoring images distorted by atmospheric turbulence is a long-standing ...
research
09/30/2020

Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

In recent years, deep learning-based methods have been successfully appl...
research
07/16/2020

Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs

Atmospheric turbulence significantly affects imaging systems which use l...
research
06/13/2022

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

Panoramic Annular Lens (PAL), composed of few lenses, has great potentia...
research
11/21/2022

Blur Interpolation Transformer for Real-World Motion from Blur

This paper studies the challenging problem of recovering motion from blu...
research
08/19/2020

LIRA: Lifelong Image Restoration from Unknown Blended Distortions

Most existing image restoration networks are designed in a disposable wa...
research
11/11/2020

Generative and Discriminative Learning for Distorted Image Restoration

Liquify is a common technique for image editing, which can be used for i...

Please sign up or login with your details

Forgot password? Click here to reset