DEEP REGRESSOR NETWORKS FOR BLIND IMAGE DEBLURRING

• Autor(a) principal: Pires, Rafael G. [UNESP]
• Data de Publicação: 2021
• Outros Autores: Santos, Daniel F.S. [UNESP], Passos, Leandro A. [UNESP], Papa, João P. [UNESP]
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1109/IGARSS47720.2021.9554775; http://hdl.handle.net/11449/241822
• topic: Blind Deconvolution; Deep learning; Image Restoration; Remote sensing

Image restoration concerns mainly smoothing noise and deblurring images that were corrupted either during acquisition or transmission. Since traditional deconvolution filters are highly dependent on specific kernels or prior knowledge to guide the deblurring process, image blur classification and further parameter estimation are critical for blind image deblurring. This paper tackles the problem in three steps: (i) it first identifies the blur type for each input image, (ii) then it estimates the respective kernel parameter, and (iii) finally, it uses deconvolution filters to restore the blurred image. The proposed approach, called Deep Regressor Networks, showed promising results in general-purpose and remote sensing image datasets corrupted by different types and blur levels than some state-of-the-art techniques.