Skip to Main content Skip to Navigation
Conference papers

Joint denoising and decompression using CNN regularization

Abstract : Wavelet compression schemes (such as JPEG2000) lead to very specific visual artifacts due to the quantization of noisy wavelet coefficients. They have highly spatialy-correlated structure that makes 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 contained in a stateof-the-art denoising CNN.
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01825573
Contributor : Andrés Almansa Connect in order to contact the contributor
Submitted on : Thursday, August 22, 2019 - 4:40:53 PM
Last modification on : Tuesday, December 8, 2020 - 9:53:21 AM
Long-term archiving on: : Friday, January 10, 2020 - 2:13:00 PM

File

main (2).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01825573, version 1
`

Citation

Mario González, Javier Preciozzi, Pablo Musé, Andrés Almansa. Joint denoising and decompression using CNN regularization. CVPR Workshop and Challenge on Learned Image Compression (CVPR 2018), IEEE/CVF, Jun 2018, Salt Lake City, UT, United States. ⟨hal-01825573⟩

Share

Metrics

Record views

136

Files downloads

80