2020/04/26 by Saeed Anwar, Anwar, Saeed, Cong Phuoc Huynh +3
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2004.13523
Accepted in CVPRW. arXiv admin note: substantial text overlap with arXiv:1712.02933
arxiv created 2020/04/26 · arxiv updated 2020/04/29
We propose to learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on the residual architecture for image denoising. Our network structure possesses three distinctive features that are important for the noise removal task. Firstly, each unit employs identity mappings as the skip connections and receives pre-activated input to preserve the gradient magnitude propagated in both the forward and backward directions. Secondly, by utilizing dilated kernels for the convolution layers in the residual branch, each neuron in the last convolution layer of each module can observe the full receptive field of the first layer. Lastly, we employ the residual on the residual architecture to ease the propagation of the high-level information. Contrary to current state-of-the-art real denoising networks, we also present a straightforward and single-stage network for real image denoising. The proposed network produces remarkably higher numerical accuracy and better visual image quality than the classical state-of-the-art and CNN algorithms when being evaluated on the three conventional benchmark and three real-world datasets.