TY - GEN
T1 - Joint denoising and decompression using CNN regularization
AU - González, Mario
AU - Preciozzi, Javier
AU - Musé, Pablo
AU - Almansa, Andrés
N1 - Publisher Copyright:
© 2019 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Wavelet compression schemes such as JPEG2000 may lead to very specific visual artifacts due to quantization of noisy wavelet coefficients. These artifacts have highly spatially-correlated structure, making it difficult to be removed with standard denoising algorithms. In this work, we propose a joint denoising and decompression method that combines a data-fitting term, which takes into account the quantization process, and an implicit prior learnt using a state-of-the-art denoising CNN.
AB - Wavelet compression schemes such as JPEG2000 may lead to very specific visual artifacts due to quantization of noisy wavelet coefficients. These artifacts have highly spatially-correlated structure, making it difficult to be removed with standard denoising algorithms. In this work, we propose a joint denoising and decompression method that combines a data-fitting term, which takes into account the quantization process, and an implicit prior learnt using a state-of-the-art denoising CNN.
UR - https://www.scopus.com/pages/publications/85078728598
M3 - Conference contribution
AN - SCOPUS:85078728598
SN - 9781538661000
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 2598
EP - 2601
BT - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Y2 - 18 June 2018 through 22 June 2018
ER -