Blind Image Deblurring with FFT-ReLU Sparsity Prior
This addresses the problem of recovering sharp images from blurred ones without prior knowledge of the blur kernel, which is incremental as it builds on existing methods with improved efficiency.
The paper tackles blind image deblurring by introducing a method that uses an FFT-ReLU sparsity prior to estimate blur kernels, achieving competitive results with state-of-the-art algorithms and up to two times faster inference.
Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. It is a small data problem, since the key challenge lies in estimating the unknown degrees of blur from a single image or limited data, instead of learning from large datasets. The solution depends heavily on developing algorithms that effectively model the image degradation process. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types. In our extensive empirical analysis, our algorithm achieves results that are competitive with the state-of-the-art blind image deblurring algorithms, and it offers up to two times faster inference, making it a highly efficient solution.