RIDNet: Recursive Information Distillation Network for Color Image Denoising

Shengkai Zhuo, Zhi Jin, Wenbin Zou, Xia Li; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

Abstract


Color image denoising is more challenging in effectiveness when compared with the grayscale one. Most existing methods play a certain role in efficiency or flexibility, but lack robustness to handle various noise levels, especially the severe noise. This keeps them away from being practically applied to color image denoising. To address this issue, we propose a robust CNN based denoiser, namely Recursive Information Distillation Network (RIDNet), to handle the denoising task at high noise levels. The proposed RIDNet simultaneously keeps the efficiency and flexibility by introducing the information distillation module and merging a tunable noise level map as the input, respectively. Experiment results on Additive White Gaussian Noise (AWGN) images demonstrate that our method outperforms most of the state-of-the-art color image denoisers.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhuo_2019_ICCV,
author = {Zhuo, Shengkai and Jin, Zhi and Zou, Wenbin and Li, Xia},
title = {RIDNet: Recursive Information Distillation Network for Color Image Denoising},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}