面向隐式神经表示的内容感知频率编码与傅里叶-切比雪夫特征
Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features
CAFE 用多个并行线性层经 Hadamard 积合成可学习的频率基，替代固定傅里叶基，可直接替换 NeRF、SIREN 类隐式表示中的位置编码模块，缓解谱偏置、提升高频细节重建；CAFE+ 再叠加切比雪夫特征作为互补，为视觉中的坐标型 MLP 提供更稳定的频率表征方案。
原文依据 we propose Content-Aware Frequency Encoding (CAFE), which builds upon Fourier features through multiple parallel linear layers combined via a Hadamard product
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论隐式神经表示（INR）已成为多种信号处理任务的强大范式，但其固有的谱偏置限制了捕获高频细节的能力。现有方法通过使用基于傅里叶的特征部分缓解了这一问题，而这些特征通常依赖固定的频率基。这迫使多层感知机（MLP）低效地组合所需的频率，从而约束了其表示能力。为解决这一局限，我们提出内容感知频率编码（CAFE），它在傅里叶特征的基础上，通过多个并行线性层并以 Hadamard 积进行组合来构建。CAFE 能够显式且高效地合成更广泛的频率基，同时学习到的权重可实现任务相关频率的选择。此外，我们将该框架扩展为 CAFE+，引入切比雪夫特征作为傅里叶基的互补成分。这一组合提供了更强、更稳定的频率表示。在多个基准上的大量实验验证了我们方法的有效性与高效性，始终优于现有方法。我们的代码可在 https://github.com/JunboKe0619/CAFE 获取。
英文原文摘要 1268 字符
Implicit Neural Representations (INRs) have emerged as a powerful paradigm for various signal processing tasks, but their inherent spectral bias limits the ability to capture high-frequency details. Existing methods partially mitigate this issue by using Fourier-based features, which usually rely on fixed frequency bases. This forces multi-layer perceptrons (MLPs) to inefficiently compose the required frequencies, thereby constraining their representational capacity. To address this limitation, we propose Content-Aware Frequency Encoding (CAFE), which builds upon Fourier features through multiple parallel linear layers combined via a Hadamard product. CAFE can explicitly and efficiently synthesize a broader range of frequency bases, while the learned weights enable the selection of task-relevant frequencies. Furthermore, we extend this framework to CAFE+, which incorporates Chebyshev features as a complementary component to Fourier bases. This combination provides a stronger and more stable frequency representation. Extensive experiments across multiple benchmarks validate the effectiveness and efficiency of our approach, consistently achieving superior performance over existing methods. Our code is available at https://github.com/JunboKe0619/CAFE.