Modeling Realistic Degradations in Non-blind Deconvolution
This addresses the sensitivity of existing deblurring methods to realistic image degradations, offering a more robust solution for image processing applications.
The paper tackles the problem of image deblurring by proposing a variational framework that models realistic degradations like pixel saturation, noise, quantization, and non-linear camera response, leading to significant improvements in image quality and PSNR.
Most image deblurring methods assume an over-simplistic image formation model and as a result are sensitive to more realistic image degradations. We propose a novel variational framework, that explicitly handles pixel saturation, noise, quantization, as well as non-linear camera response function due to e.g., gamma correction. We show that accurately modeling a more realistic image acquisition pipeline leads to significant improvements, both in terms of image quality and PSNR. Furthermore, we show that incorporating the non-linear response in both the data and the regularization terms of the proposed energy leads to a more detailed restoration than a naive inversion of the non-linear curve. The minimization of the proposed energy is performed using stochastic optimization. A dataset consisting of realistically degraded images is created in order to evaluate the method.