Variational models for joint subsampling and reconstruction of turbulence-degraded images

TL;DR

This paper introduces a variational model that jointly selects the best frames and reconstructs a clear, high-quality image from turbulence-degraded video sequences, improving image restoration accuracy.

Contribution

The work presents a novel variational framework for simultaneous frame subsampling and image reconstruction tailored for turbulence-distorted videos.

Findings

Significantly improved image quality through joint subsampling and reconstruction.

Effective frame selection enhances the accuracy of turbulence compensation.

The model can be integrated into existing algorithms for better results.

Abstract

Turbulence-degraded image frames are distorted by both turbulent deformations and space-time-varying blurs. To suppress these effects, we propose a multi-frame reconstruction scheme to recover a latent image from the observed image sequence. Recent approaches are commonly based on registering each frame to a reference image, by which geometric turbulent deformations can be estimated and a sharp image can be restored. A major challenge is that a fine reference image is usually unavailable, as every turbulence-degraded frame is distorted. A high-quality reference image is crucial for the accurate estimation of geometric deformations and fusion of frames. Besides, it is unlikely that all frames from the image sequence are useful, and thus frame selection is necessary and highly beneficial. In this work, we propose a variational model for joint subsampling of frames and extraction of a clear image. A fine image and a suitable choice of subsample are simultaneously obtained by iteratively reducing an energy functional. The energy consists of a fidelity term measuring the discrepancy between the extracted image and the subsampled frames, as well as regularization terms on the extracted image and the subsample. Different choices of fidelity and regularization terms are explored. By carefully selecting suitable frames and extracting the image, the quality of the reconstructed image can be significantly improved. Extensive experiments have been carried out, which demonstrate the efficacy of our proposed model. In addition, the extracted subsamples and images can be put in existing algorithms to produce improved results.