Enhancing Border Learning for Better Image Denoising

Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematics (Basel) Ročník 13; číslo 7; s. 1119
Hlavní autoři: Ge, Xin, Zhu, Yu, Qi, Liping, Hu, Yaoqi, Sun, Jinqiu, Zhang, Yanning
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.04.2025
Témata:
Accuracy
Algorithms
Analysis
Artificial neural networks
autoencoder
border effect
Borders
convolutional neural network
Deep learning
Design
image denoising
Machine learning
Neural networks
Noise reduction
padding
patch-based method
United States
New Jersey
ISSN:2227-7390, 2227-7390
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at the borders of output images, referred to as border effects, which negatively impact the network’s ability to learn effective features. In traditional methods, these border effects, associated with convolutional/deconvolutional operations, have been mitigated using patch-based techniques. Inspired by this observation, patch-wise denoising algorithms were explored to derive a CNN architecture that avoids border effects. Specifically, we extend the patch-wise autoencoder to learn image mappings through patch extraction and patch-averaging operations, demonstrating that the patch-wise autoencoder is equivalent to a specific convolutional neural network (CNN) architecture, resulting in a novel residual block. This new residual block includes a mask that enhances the CNN’s ability to learn border features and eliminates border artifacts, referred to as the Border-Enhanced Residual Block (BERBlock). By stacking BERBlocks, we constructed a U-Net denoiser (BERUNet). Experiments on public datasets demonstrate that the proposed BERUNet achieves outstanding performance. The proposed network architecture is built on rigorous mathematical derivations, making its working mechanism highly interpretable. The code and all pretrained models are publicly available.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2227-7390
2227-7390
DOI:10.3390/math13071119