ML Anthology

Joint Denoising and Decompression Using CNN Regularization

Mario González, Javier Preciozzi, Pablo Musé, Andrés Almansa
CVPRW 2018 pp. 2598-2601
/cvprw/2018/gonzalez2018cvprw-joint/

Abstract

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 re- moved 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.

PDF CVPRW Semantic Scholar

Cite

Text

González et al. "Joint Denoising and Decompression Using CNN Regularization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.

Markdown

[González et al. "Joint Denoising and Decompression Using CNN Regularization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/gonzalez2018cvprw-joint/)

BibTeX

@inproceedings{gonzalez2018cvprw-joint,
  title     = {{Joint Denoising and Decompression Using CNN Regularization}},
  author    = {González, Mario and Preciozzi, Javier and Musé, Pablo and Almansa, Andrés},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {2598-2601},
  url       = {https://mlanthology.org/cvprw/2018/gonzalez2018cvprw-joint/}
}