Published Paper Details:

Real photographs frequently contain complex blur, such as the combination of space-variant and space-invariant blur, which is challenging to mathematically represent. In this work, we provide a cutting-edge blur kernel-free picture deblurring technique. We use two photographs, one fuzzy with low shutter speed and low ISO noise, and the other noisy with fast shutter speed and high ISO noise, both of which may be easily obtained in low-light conditions. By dividing the blurred picture into patches, we can use the corresponding patches in the noisy image to extend the Gaussian mixture model (GMM) and describe the underlying intensity distribution of each patch. Utilizing an analysis of the optical flow between the two pictures, we generate patch correspondences. The Expectation Maximization (EM) algorithm is utilized to estimate the parameters of GMM. To preserve sharp features, we add an additional bilateral term to the objective function in the M-step. We eventually add a detail layer to the deblurred image for refinement. Extensive experiments on both synthetic and real-world data demonstrate that our method outperforms state-of-the terms of robustness, visual quality, and quantitative metrics.