English

Modeling Realistic Degradations in Non-blind Deconvolution

Computer Vision and Pattern Recognition 2018-06-05 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1806.01097,
  title  = {Modeling Realistic Degradations in Non-blind Deconvolution},
  author = {Jérémy Anger and Mauricio Delbracio and Gabriele Facciolo},
  journal= {arXiv preprint arXiv:1806.01097},
  year   = {2018}
}

Comments

Accepted at the 2018 IEEE International Conference on Image Processing (ICIP 2018)

R2 v1 2026-06-23T02:18:08.984Z