HDW-SR：基于小波分解的高频引导扩散模型用于图像超分辨率
HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution
把扩散过程限制在残差图上、并用小波子带做稀疏交叉注意力提供高频显式引导，这套「频域分解 + 残差扩散」思路可直接迁移到去模糊、去噪、压缩伪影去除等其它复原任务的高频细节恢复。
原文依据 we perform diffusion only on the residual map, allowing the network to focus more effectively on high-frequency information restoration
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于扩散的方法在单图像超分辨率（SISR）中展现出很大潜力；然而，现有方法由于在高频域缺乏充分引导，往往产生模糊的细节。为解决该问题，我们提出一种基于小波分解的高频引导扩散网络（HDW-SR），用以替换扩散框架中传统的 U-Net 骨干网络。具体而言，我们仅在残差图上执行扩散，使网络能够更有效地聚焦于高频信息恢复。随后，我们引入基于小波的下采样替代标准 CNN 下采样，以实现多尺度频率分解，从而在预超分辨率图像的高频子带与扩散图像的低频子带之间建立稀疏交叉注意力，实现显式的高频引导。此外，我们设计了动态阈值模块（DTB），在稀疏注意力过程中细化高频选择。在上采样阶段，小波变换的可逆性保证了低损失的特征重建。在合成数据集与真实世界数据集上的实验表明，HDW-SR 取得了有竞争力的超分辨率性能，尤其在恢复细粒度图像细节方面表现突出。代码见 https://github.com/Baty2023/HDW-SR。
英文原文摘要 1357 字符
Diffusion-based methods have shown great promise in single image super-resolution (SISR); however, existing approaches often produce blurred fine details due to insufficient guidance in the high-frequency domain. To address this issue, we propose a High-Frequency Guided Diffusion Network based on Wavelet Decomposition (HDW-SR), which replaces the conventional U-Net backbone in diffusion frameworks. Specifically, we perform diffusion only on the residual map, allowing the network to focus more effectively on high-frequency information restoration. We then introduce wavelet-based downsampling in place of standard CNN downsampling to achieve multi-scale frequency decomposition, enabling sparse cross-attention between the high-frequency subbands of the pre-super-resolved image and the low-frequency subbands of the diffused image for explicit high-frequency guidance. Moreover, a Dynamic Thresholding Block (DTB) is designed to refine high-frequency selection during the sparse attention process. During upsampling, the invertibility of the wavelet transform ensures low-loss feature reconstruction. Experiments on both synthetic and real-world datasets demonstrate that HDW-SR achieves competitive super-resolution performance, excelling particularly in recovering fine-grained image details. Code is available at https://github.com/Baty2023/HDW-SR.