Scholarlink

<p>Recent advances in deep learning, particularly generative adversarial networks (GANs), have significantly advanced image inpainting. However, reconstructing structural details and accurate chromaticity distributions in complex scenes remains challenging. This paper proposes a GAN-based method via dual-domain perception and cross-domain collaboration for image inpainting, including spatial-frequency guided attention module, frequency-spatial collaborative attention module and adaptive spatial-channel feature aggregation module. The spatial-frequency guided attention module leverages spatial features to refine frequency-domain components from Fast Fourier Transform, highlighting structural and textural information. The frequency-spatial collaborative attention module optimizes chromaticity and edge details through amplitude and phase guidance from Inverse Fast Fourier Transform. Finally, the adaptive spatial-channel feature aggregation module fuses spatial and channel features, then dynamically modulates chromatic-aware and edge-aware features. Evaluation results on public datasets demonstrate superior performance in reducing chromaticity deviations and edge blurring compared with the state-of-the-art methods. The code will be available at <a href="https://github.com/RRChen001/SFNet">https://github.com/RRChen001/SFNet</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

Dual-domain perception and cross-domain collaboration guidance network for image inpainting

  • 期刊论文

  • 发表日期：

    2026年2月3日

查看全文
  • Lili Shen,
  • Ran Chen,
  • Ye Sun,
  • Yu Wang,
  • Qi Li,
  • Jiahao Wen

摘要

Recent advances in deep learning, particularly generative adversarial networks (GANs), have significantly advanced image inpainting. However, reconstructing structural details and accurate chromaticity distributions in complex scenes remains challenging. This paper proposes a GAN-based method via dual-domain perception and cross-domain collaboration for image inpainting, including spatial-frequency guided attention module, frequency-spatial collaborative attention module and adaptive spatial-channel feature aggregation module. The spatial-frequency guided attention module leverages spatial features to refine frequency-domain components from Fast Fourier Transform, highlighting structural and textural information. The frequency-spatial collaborative attention module optimizes chromaticity and edge details through amplitude and phase guidance from Inverse Fast Fourier Transform. Finally, the adaptive spatial-channel feature aggregation module fuses spatial and channel features, then dynamically modulates chromatic-aware and edge-aware features. Evaluation results on public datasets demonstrate superior performance in reducing chromaticity deviations and edge blurring compared with the state-of-the-art methods. The code will be available at https://github.com/RRChen001/SFNet.