Published on Mon Mar 02 2020

Flashlight CNN Image Denoising

Pham Huu Thanh Binh, Cristóvão Cruz, Karen Egiazarian

This paper proposes a learning-based denoising method called FlashLight CNN. The proposed approach is based on deep residual networks and inception networks. It is able to leverage many more parameters than residual networks alone.

0
0
0
Abstract

This paper proposes a learning-based denoising method called FlashLight CNN (FLCNN) that implements a deep neural network for image denoising. The proposed approach is based on deep residual networks and inception networks and it is able to leverage many more parameters than residual networks alone for denoising grayscale images corrupted by additive white Gaussian noise (AWGN). FlashLight CNN demonstrates state of the art performance when compared quantitatively and visually with the current state of the art image denoising methods.

Tue Dec 31 2019
Computer Vision
Deep Learning on Image Denoising: An overview
0
0
0
Sun Oct 28 2018
Computer Vision
Enhanced CNN for image denoising
Deep convolutional neural networks (CNNs) are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii) Deeper networks face the challenge of performance saturation.
0
0
0
Thu Oct 11 2018
Computer Vision
Deep Learning for Image Denoising: A Survey
Deep learning technology has received a great deal of attention and has been widely applied in the field of imaging processing. In this paper, we aim to review and summarize the deep learning technologies for image denoising proposed in recent years.
0
0
0
Tue Nov 21 2017
Computer Vision
Universal Denoising Networks : A Novel CNN Architecture for Image Denoising
We design a novel network architecture for learning discriminative image metrics. The proposed models are able to handle a wide range of noise levels using a single set of learned parameters. They are very robust when the noise degrading the latent image does not match the statistics of the noise used during training.
0
0
0
Wed Jun 14 2017
Computer Vision
When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
The code is available online. The paper was written by Ding-Liu Liu. It is the first work investigating the benefit of exploiting image semantics simultaneously.
0
0
0
Sun Apr 26 2020
Computer Vision
Identity Enhanced Residual Image Denoising
We propose to learn a fully-convolutional network model that consists of aChain of Identity Mapping Modules and residual on the residual architecture. The proposed network produces remarkably higher numerical accuracy and better visual image quality than the classical state-of-the-art and CNN algorithms.
0
0
0