BM3D vs 2-Layer ONN

03/04/2021
by   Junaid Malik, et al.
0

Despite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs. Older but computationally more efficient methods such as BM3D remain a popular choice, especially in resource-constrained scenarios. In this study, we aim to find out whether compact neural networks can learn to produce competitive results as compared to BM3D for AWGN image denoising. To this end, we configure networks with only two hidden layers and employ different neuron models and layer widths for comparing the performance with BM3D across different AWGN noise levels. Our results conclusively show that the recently proposed self-organized variant of operational neural networks based on a generative neuron model (Self-ONNs) is not only a better choice as compared to CNNs, but also provide competitive results as compared to BM3D and even significantly surpass it for high noise levels.

READ FULL TEXT
research
03/04/2021

Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising

Real-world blind denoising poses a unique image restoration challenge du...
research
11/29/2021

Image denoising by Super Neurons: Why go deep?

Classical image denoising methods utilize the non-local self-similarity ...
research
09/01/2020

Operational vs Convolutional Neural Networks for Image Denoising

Convolutional Neural Networks (CNNs) have recently become a favored tech...
research
11/28/2020

Lattice Fusion Networks for Image Denoising

A novel method for feature fusion in convolutional neural networks is pr...
research
07/17/2022

2D Self-Organized ONN Model For Handwritten Text Recognition

Deep Convolutional Neural Networks (CNNs) have recently reached state-of...
research
04/24/2020

Self-Organized Operational Neural Networks with Generative Neurons

Operational Neural Networks (ONNs) have recently been proposed to addres...

Please sign up or login with your details

Forgot password? Click here to reset