Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Gladys Mange,
  • Jorge Marx Gómez,
  • Ronald Waweru,
  • Michael Kimwele

摘要

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.