R1.pdf (3.5 MB)
Hierarchical Residual Learning for Image Denoising
journal contribution
posted on 2019-05-13, 13:08 authored by W Shi, F Jiang, S Zhang, R Wang, D Zhao, H ZhouIn recent years, residual learning based convolutional neural networks have been
applied to image restoration and achieved some success. To avoid network degradation, deep layers in these methods are identity mappings, which are not easy
to be learned as observed in recent image recognition work. In this paper, we
propose a novel residual learning based CNN framework for image denoising,
which does not need to learn identify mappings while avoiding network degradation. The proposed CNN network contains three kinds of sub-networks: feature
extraction sub-network, inference sub-network and fusion sub-network. The
feature extraction sub-network is first used to densely extract patches and represent them as high dimensional feature maps. Multiple inference sub-networks
are then cascaded to learn noise maps by exploiting multi-scale information in
a hierarchical fashion, which makes our method have a strong ability of toleraing errors in noise estimation. Finally, the fusion sub-network fuses the noise
maps to obtain the final noise estimation. The proposed hierarchical residual
learning network can tackle with multiple general image denoising tasks such
as Gaussian denoising and single image super-resolution. Experimental results
on several datasets show that our hierarchical residual learning based image
denoising method outperforms many state-of-the-art ones.
Funding
This work has been supported in part by the Major State Basic Research Development Program of China (973 Program 2015CB351804), the National Science Foundation of China under Grant No. 61572155. H. Zhou was supported by UK EPSRC under Grant EP/N011074/1, Royal Society-Newton Advanced Fellowship under Grant NA160342, and European Unions Horizon 2020 research and innovation program under the Marie-Sklodowska-Curie grant agreement No 720325
History
Citation
Signal Processing: Image Communication, 2019, 76, pp. 243-251Author affiliation
/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of InformaticsVersion
- AM (Accepted Manuscript)