DN-ResNet: Efficient Deep Residual Network for Image Denoising

by   Haoyu Ren, et al.

A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. We propose DN-ResNet, which is a deep convolutional neural network (CNN) consisting of several residual blocks (ResBlocks). With cascade training, DN-ResNet is more accurate and more computationally efficient than the state of art denoising networks. An edge-aware loss function is further utilized in training DN-ResNet, so that the denoising results have better perceptive quality compared to conventional loss function. Next, we introduce the depthwise separable DN-ResNet (DS-DN-ResNet) utilizing the proposed Depthwise Seperable ResBlock (DS-ResBlock) instead of standard ResBlock, which has much less computational cost. DS-DN-ResNet is incrementally evolved by replacing the ResBlocks in DN-ResNet by DS-ResBlocks stage by stage. As a result, high accuracy and good computational efficiency are achieved concurrently. Whereas previous state of art deep learning methods focused on denoising either Gaussian or Poisson corrupted images, we consider denoising images having the more practical Poisson with additive Gaussian noise as well. The results show that DN-ResNets are more efficient, robust, and perform better denoising than current state of art deep learning methods, as well as the popular variants of the BM3D algorithm, in cases of blind and non-blind denoising of images corrupted with Poisson, Gaussian or Poisson-Gaussian noise. Our network also works well for other image enhancement task such as compressed image restoration.


page 11

page 13

page 15


Flashlight CNN Image Denoising

This paper proposes a learning-based denoising method called FlashLight ...

Image Denoising using Attention-Residual Convolutional Neural Networks

During the image acquisition process, noise is usually added to the data...

MindX: Denoising Mixed Impulse Poisson-Gaussian Noise Using Proximal Algorithms

We present a novel algorithm for blind denoising of images corrupted by ...

Deep Convolutional Denoising of Low-Light Images

Poisson distribution is used for modeling noise in photon-limited imagin...

Multiscale Sparsifying Transform Learning for Image Denoising

The data-driven sparse methods such as synthesis dictionary learning and...

Fast and Flexible Image Blind Denoising via Competition of Experts

Fast and flexible processing are two essential requirements for a number...

Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks

Demosaicking and denoising are among the most crucial steps of modern di...

Please sign up or login with your details

Forgot password? Click here to reset