Infrared image deturbulence restoration using degradation parameter-assisted wide & deep learning

Infrared images captured under turbulent conditions are often degraded by complex geometric distortions and blurring, which substantially compromise image clarity and subsequent analysis. In this paper, we recast the infrared deturbulence problem as a more general image restoration task and propose a parameter assisted image restoration method that leverages degradation prior information from the turbulent infrared images. Specifically, we propose an ingenious and efficient multi-frame image restoration network (DparNet) with wide & deep architecture, which integrates degraded images and prior knowledge of degradation to reconstruct images with ideal clarity and stability. The degradation prior is directly learned from degraded images in form of key degradation parameter matrix, with no requirement of any off-site knowledge. The wide & deep architecture in DparNet enables the learned parameters to directly modulate the final restoring results, boosting spatial & intensity adaptive image restoration. We demonstrate the proposed method on infrared image deturbulence by constructing a dedicated dataset of 49,744 images to rigorously evaluate its performance under challenging turbulence degradation. To further validate the generality of our approach, a supplementary visible image denoising experiment was also conducted on a larger dataset containing 109,536 images. The experimental results show that our DparNet significantly outperform SoTA methods in restoration performance and network efficiency. More importantly, by utilizing the learned degradation parameters via wide & deep learning, we can improve the PSNR of image restoration by 0.6∼1.1 dB with less than 2% increasing in model parameter numbers and computational complexity. Our work suggests that degraded images may hide key information of the degradation process, which can be utilized to boost spatial & intensity adaptive image restoration.