Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior

07/17/2017
by   Peng Liu, et al.
0

We explore an innovative strategy for image denoising by using convolutional neural networks (CNN) to learn similar pixel-distribution features from noisy images. Many types of image noise follow a certain pixel-distribution in common, such as additive white Gaussian noise (AWGN). By increasing CNN's width with larger reception fields and more channels in each layer, CNNs can reveal the ability to extract more accurate pixel-distribution features. The key to our approach is a discovery that wider CNNs with more convolutions tend to learn the similar pixel-distribution features, which reveals a new strategy to solve low-level vision problems effectively that the inference mapping primarily relies on the priors behind the noise property instead of deeper CNNs with more stacked nonlinear layers. We evaluate our work, Wide inference Networks (WIN), on AWGN and demonstrate that by learning pixel-distribution features from images, WIN-based network consistently achieves significantly better performance than current state-of-the-art deep CNN-based methods in both quantitative and visual evaluations. Code and models are available at <https://github.com/cswin/WIN>.

READ FULL TEXT

page 3

page 7

page 11

page 12

page 13

page 14

page 15

page 16

research
07/28/2017

Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising

In this work, we explore an innovative strategy for image denoising by u...
research
10/20/2019

KRNET: Image Denoising with Kernel Regulation Network

One popular strategy for image denoising is to design a generalized regu...
research
04/27/2022

A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising

Recently, convolutional neural networks (CNNs) and attention mechanisms ...
research
09/14/2022

Considering Image Information and Self-similarity: A Compositional Denoising Network

Recently, convolutional neural networks (CNNs) have been widely used in ...
research
04/02/2021

Variational Deep Image Denoising

Convolutional neural networks (CNNs) have shown outstanding performance ...
research
02/07/2019

DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling

We propose DoPAMINE, a new neural network based multiplicative noise des...
research
12/22/2021

Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising

Image denoising is of vital importance in many imaging or computer visio...

Please sign up or login with your details

Forgot password? Click here to reset