Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features
This work addresses a bottleneck in INR-based signal processing for researchers and practitioners, offering an incremental improvement over existing Fourier feature methods.
The paper tackles the limitation of Implicit Neural Representations (INRs) in capturing high-frequency details due to spectral bias by proposing Content-Aware Frequency Encoding (CAFE) and its extension CAFE+, which use learned frequency bases to improve efficiency and performance. The method consistently achieves superior results across multiple benchmarks, though no specific numerical gains are provided in the abstract.
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.