Skip to main navigation Skip to search Skip to main content

DNLN: image super-resolution with deformable non-local attention and multi-branch weighted feature fusion

  • Jiaxin Chen
  • , Dong Xing
  • , Mohammad Shabaz
  • , Yongpei Zhu
  • , Yong Wang
  • , Xianxun Zhu*
  • *Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Single image super-resolution (SISR) aims to recover a high-resolution image from a low-resolution input. Despite recent advancements, existing methods often fail to fully exploit self-similarities across image scales. In this paper, we introduce the Deformable Non-Local (D-NL) attention module, integrated into a recurrent neural network. The D-NL attention mechanism leverages deformable convolutions to better capture pixel-wise correlations and long-range self-similarities. Additionally, we propose a Multi-Scale Channel Attention Module (MS-CAM) and a Multi-Branch Weighted Feature Fusion (MWFF) cell to enhance feature fusion, effectively identifying and combining features with distinct semantics and scales. Experimental results on benchmark datasets demonstrate that our approach, DNLN, significantly outperforms state-of-the-art methods, underscoring the effectiveness of exploiting long-range self-similarities for SISR.

Original languageEnglish
Article number105721
Pages (from-to)1-8
Number of pages8
JournalImage and Vision Computing
Volume162
DOIs
Publication statusPublished - Oct 2025

Keywords

  • Deformable non-local attention
  • Multi-scale channel attention module
  • Multi-branch weighted feature fusion

Fingerprint

Dive into the research topics of 'DNLN: image super-resolution with deformable non-local attention and multi-branch weighted feature fusion'. Together they form a unique fingerprint.

Cite this