Identity Enhanced Residual Image Denoising

Abstract

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.

Accepted in CVPRW. arXiv admin note: substantial text overlap with arXiv:1712.02933

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Feature Pyramid Networks for Object Detection
• RENOIR - A Dataset for Real Low-Light Image Noise Reduction
• Real-world Noisy Image Denoising: A New Benchmark
• On Rendering Synthetic Images for Training an Object Detector
• Monte Carlo non local means: Random sampling for large-scale image filtering