Scholarlink

<p>In recent years, image super-resolution (SR) based on deep learning has achieved great success. However, the current state-of-the-art (SOTA) models still face the problem of high computational cost. Lightweight image super-resolution models are extremely important for practical applications, and reducing the number of parameters and FLOPS is the key to designing lightweight super-resolution models. To this end, an Inception-like large kernel network (ILKN) is proposed in this paper. Specifically, we design the basic components of the Inception-like large kernel structure to form the backbone network of ILKN and introduce a more efficient large kernel attention module to reduce the computational cost while improving the performance. Experimental results show that for different scales (× 2, × 3, × 4) ILKN outperforms most of the existing lightweight SR methods, not only achieving close to SOTA performance, but also keeping the number of parameters and FLOPS relatively minimal. The code and model are available at <a href="https://github.com/kptx666/ILKN">https://github.com/kptx666/ILKN</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

Inception-like Large Kernel network for lightweight image super-resolution

  • 期刊论文

  • 发表日期：

    2025年1月22日

查看全文
  • Haomou Bai

摘要

In recent years, image super-resolution (SR) based on deep learning has achieved great success. However, the current state-of-the-art (SOTA) models still face the problem of high computational cost. Lightweight image super-resolution models are extremely important for practical applications, and reducing the number of parameters and FLOPS is the key to designing lightweight super-resolution models. To this end, an Inception-like large kernel network (ILKN) is proposed in this paper. Specifically, we design the basic components of the Inception-like large kernel structure to form the backbone network of ILKN and introduce a more efficient large kernel attention module to reduce the computational cost while improving the performance. Experimental results show that for different scales (× 2, × 3, × 4) ILKN outperforms most of the existing lightweight SR methods, not only achieving close to SOTA performance, but also keeping the number of parameters and FLOPS relatively minimal. The code and model are available at https://github.com/kptx666/ILKN.