提出CAFE方法，让神经隐式表示更高效捕捉高频细节。
Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features
- 用并行线性层与哈达玛积设计可学习频率编码
- 在多个基准上优于现有方法，显著提升高频建模能力
- 适合需要精细细节重建的图像/信号处理任务
隐式神经表示（INRs）在多种信号处理任务中表现强劲，但其固有的频谱偏差限制了对高频细节的捕捉。现有方法虽采用基于傅里叶的特征缓解此问题，但通常依赖固定频率基，迫使多层感知机（MLPs）低效组合所需频率，从而制约表达能力。为此，本文提出内容感知频率编码（CAFE），在傅里叶特征基础上，通过多个并行线性层结合哈达玛积，显式高效地合成更广范围的频率基，且学习权重可选择任务相关频率。进一步扩展为CAFE+，引入切比雪夫特征作为傅里叶基的补充，提供更强且更稳定的频率表示。在多个基准上的大量实验验证了该方法的有效性和效率，性能持续优于现有方法。代码已公开于https://github.com/JunboKe0619/CAFE。
原文摘要 · Abstract (English)
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.
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。