english Icono del idioma   español Icono del idioma  

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12008/43539 How to cite
Title: Modeling realistic degradations in non-blind deconvolution
Authors: Anger, Jeremy
Facciolo, Gabriele
Delbracio, Mauricio
Type: Preprint
Keywords: Non-blind deconvolution, Image deblurring, Saturation, Quantization, Gamma correction
Descriptors: Procesamiento de Señales
Issue Date: 2018
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 nonlinear 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.
Description: Trabajo presentado en 25th IEEE International Conference on Image Processing (ICIP), 2018
Citation: Anger, J, Facciolo, G, Delbracio, M. "Modeling realistic degradations in non-blind deconvolution" Publicado en: Proceedings of the 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, 7-10 oct., 2018, pp. 978-982, doi: 10.1109/ICIP.2018.8451115.
Academic department: Procesamiento de Señales
Investigation group: Tratamiento de Imágenes
License: Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
Appears in Collections:Publicaciones académicas y científicas - Instituto de Ingeniería Eléctrica

Files in This Item:
File Description SizeFormat  
AFD18.pdf2 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons