Turbulent disturbance brings about the spatially varying blur in captured images. Turbulent disturbance brings about the spatially varying blur in captured images. In this paper, we proposed a deep learning method to deal with this problem. And the way we approximate the kernel is closer to the real turbulent circumstance. Experiments on both synthetic and real images show that our proposed method can effectively mitigate the turbulent blur from a single image, quantitatively and qualitatively outperforms the single Preprint submitted to Neurocomputing August 23, 2023frame based methods as well as yields comparable results to multi-frame methods.
Deep Kernel Estimation for Turbulent Blur Correction
11.10.2023
3047616 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Range Estimation from Camera Blur by Regularized Adaptive Identification
British Library Conference Proceedings | 1993
|