Scholarlink

<p>In this paper, proposes a dual-stage feature fusion framework for single image super resolution, integrating multiple residual blocks and a multi-layer perceptron to enhance image quality. In the first stage, both low- and high-level features are extracted and fused to generate rich feature representations. The second stage applies edge-preserving blurring to refine features, effectively minimizing noise in smooth regions while maintaining structural details. Experimental results on standard benchmarks demonstrate that the proposed method consistently outperforms existing approaches in terms of Peak Signal-to-Noise Ratio and Structural Similarity Index Measure, achieving superior restoration of fine textures and edges. The framework offers a novel strategy for balancing detail preservation and noise reduction in super resolution tasks.</p>

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

MRB-MLP: dual stage feature-fusion approach to enhance super resolution quality from single images

  • 期刊论文

  • 发表日期：

    2025年9月16日

查看全文
  • Hyun Ho Han,
  • Kun-Hee Han

摘要

In this paper, proposes a dual-stage feature fusion framework for single image super resolution, integrating multiple residual blocks and a multi-layer perceptron to enhance image quality. In the first stage, both low- and high-level features are extracted and fused to generate rich feature representations. The second stage applies edge-preserving blurring to refine features, effectively minimizing noise in smooth regions while maintaining structural details. Experimental results on standard benchmarks demonstrate that the proposed method consistently outperforms existing approaches in terms of Peak Signal-to-Noise Ratio and Structural Similarity Index Measure, achieving superior restoration of fine textures and edges. The framework offers a novel strategy for balancing detail preservation and noise reduction in super resolution tasks.