用频域增强的扩散模型实现高效超分辨率，细节更清晰。
DiffFNO: Diffusion Fourier Neural Operator
- 结合加权傅里叶神经算子与注意力机制，融合频域与空间特征。
- 在不同缩放倍数下比现有方法提升2-4 dB PSNR，推理更快。
- 适合追求高精度与低延迟超分辨率的视觉应用开发者。
我们提出 DiffFNO，一种基于加权傅里叶神经算子（WFNO）的新型扩散框架，用于任意尺度超分辨率。WFNO 中的模式再平衡机制有效捕捉关键频率成分，显著提升高频图像细节的重建能力。门控融合机制（GFM）自适应地将注意力神经算子（AttnNO）的空间特征补充到 WFNO 的谱特征中，增强了对全局结构与局部细节的建模能力。自适应时间步长（ATS）ODE 求解器采用确定性采样策略，通过动态调整积分步长加速推理，且不牺牲输出质量。大量实验表明，DiffFNO 在多种缩放因子下均达到当前最优（SOTA）性能，相比现有方法在 PSNR 上提升 2–4 dB，包括超出训练分布的场景。同时具备更低的推理耗时。本方法为超分辨率任务树立了新的标准，兼具卓越精度与计算效率。
原文摘要 · Abstract (English)
We introduce DiffFNO, a novel diffusion framework for arbitrary-scale super-resolution strengthened by a Weighted Fourier Neural Operator (WFNO). Mode Rebalancing in WFNO effectively captures critical frequency components, significantly improving the reconstruction of high-frequency image details that are crucial for super-resolution tasks. Gated Fusion Mechanism (GFM) adaptively complements WFNO's spectral features with spatial features from an Attention-based Neural Operator (AttnNO). This enhances the network's capability to capture both global structures and local details. Adaptive Time-Step (ATS) ODE solver, a deterministic sampling strategy, accelerates inference without sacrificing output quality by dynamically adjusting integration step sizes ATS. Extensive experiments demonstrate that DiffFNO achieves state-of-the-art (SOTA) results, outperforming existing methods across various scaling factors by a margin of 2-4 dB in PSNR, including those beyond the training distribution. It also achieves this at lower inference time. Our approach sets a new standard in super-resolution, delivering both superior accuracy and computational efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。