Improving Image Denoising Performance With CNN-Attention-Like Encoder Layers

Gladys Mange (), Jorge Marx Gómez, Ronald Waweru and Michael Kimwele
Additional contact information
Gladys Mange: KCA University, School of Technology (SOT)
Jorge Marx Gómez: Oldenburg University
Ronald Waweru: Jomo Kenyatta University of Agriculture and Technology
Michael Kimwele: Jomo Kenyatta University of Agriculture and Technology

A chapter in Advancement in Embedded and Mobile Systems, 2026, pp 337-349 from Springer

Abstract: Abstract Image denoising is a fundamental task in computer vision, critical for improving image quality in a variety of applications. This research presents a novel technique for image denoising that employs dual Convolutional Neural Network (CNN) encoders and attention-based decoders. This research uses the strengths of attention mechanisms to selectively reconstitute features retrieved by encoders, improving the quality of denoised images. Furthermore, it offers a method for combining attention maps from various encoders to improve the denoising process. In terms of objective quality and its capacity to reduce noise, the CNN with Attention (CNWATT2) denoising technique performs better than the previously employed denoising models.

Keywords: Convolutional neural network; Attention mechanism; Batch renormalization; Encoder; Decoder; Image denoising (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prochp:978-3-031-99219-3_23

Ordering information: This item can be ordered from
http://www.springer.com/9783031992193

DOI: 10.1007/978-3-031-99219-3_23

Access Statistics for this chapter

More chapters in Progress in IS from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().