arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.01028cs.CVcs.AI
收藏

面向隐式神经表示的内容感知频率编码 with 傅里叶-切比雪夫特征

Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features

School of Mathematics and Statistics, Hunan Normal University(湖南师范大学数学与统计学学院);Department of Statistics and Data Science, Southern University of Science and Technology(南方科技大学统计与数据科学系)

Junbo Ke, Yangyang Xu, You-Wei Wen, Chao Wang

AI总结:

本文提出CAFE方法,通过傅里叶-切比雪夫特征提升隐式神经表示的高频捕捉能力,实验验证其在多个基准上的优越性能。

摘要:

隐式神经表示(INRs)已作为一种强大的范式应用于各种信号处理任务,但其固有的频谱偏倚限制了捕捉高频细节的能力。现有方法部分缓解这一问题通过使用傅里叶基特征,通常依赖于固定的频率基。这迫使多层感知机(MLPs)低效地组合所需的频率,从而限制了其表示能力。为了解决这一限制,我们提出了内容感知频率编码(CAFE),它通过多个并行线性层结合哈达玛积来构建傅里叶特征。CAFE可以显式且高效地合成更广泛的频率基,而学习的权重使能够选择任务相关的频率。此外,我们将这一框架扩展到CAFE+,它将切比雪夫特征作为傅里叶基的补充组件。这种结合提供了更强且更稳定的频率表示。在多个基准上的广泛实验验证了我们方法的有效性和效率,一致地在现有方法上取得了更优的性能。我们的代码可在https://github.com/JunboKe0619/CAFE上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑