Scholarlink

<p>Swin transformer-based methods have achieved impressive performance in image super-resolution (SR) due to their ability to effectively model long-range spatial dependencies. However, the core component, window-based self-attention (WSA), introduces considerable computational overhead, which limits their applicability on resource-constrained devices. To address these issues, we propose a Swin-style shifted pooling cross-aggregation network (SPCAN) for image SR, which achieves high computational efficiency while maintaining excellent reconstruction quality. Specifically, we adopt max pooling-based downsampling as a lightweight alternative to WSA for extracting low-frequency features and introduce a shifted pooling mechanism that emulates the shifted window strategy of Swin transformers within a convolutional neural network (CNN) framework. This mechanism is embedded within a cross-aggregation module to facilitate efficient inter-region feature interaction. Moreover, we generalize the pooling operation from square to rectangular regions to enhance the model’s ability to capture spatial dependencies across different orientations. Extensive experiments on public SR benchmarks demonstrate that the proposed method achieves competitive reconstruction accuracy while offering significantly better efficiency compared with existing state-of-the-art methods. The source code and pretrained models are available at: <a href="https://github.com/hms-source/SPCAN">https://github.com/hms-source/SPCAN</a>.</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

A Swin-style shifted pooling cross-aggregation network for efficient image super-resolution

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月20日

查看全文
  • Rui He,
  • Zhenyang Zhu,
  • Xiaoyang Mao

摘要

Swin transformer-based methods have achieved impressive performance in image super-resolution (SR) due to their ability to effectively model long-range spatial dependencies. However, the core component, window-based self-attention (WSA), introduces considerable computational overhead, which limits their applicability on resource-constrained devices. To address these issues, we propose a Swin-style shifted pooling cross-aggregation network (SPCAN) for image SR, which achieves high computational efficiency while maintaining excellent reconstruction quality. Specifically, we adopt max pooling-based downsampling as a lightweight alternative to WSA for extracting low-frequency features and introduce a shifted pooling mechanism that emulates the shifted window strategy of Swin transformers within a convolutional neural network (CNN) framework. This mechanism is embedded within a cross-aggregation module to facilitate efficient inter-region feature interaction. Moreover, we generalize the pooling operation from square to rectangular regions to enhance the model’s ability to capture spatial dependencies across different orientations. Extensive experiments on public SR benchmarks demonstrate that the proposed method achieves competitive reconstruction accuracy while offering significantly better efficiency compared with existing state-of-the-art methods. The source code and pretrained models are available at: https://github.com/hms-source/SPCAN.