# Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations Source: [Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations]() Collection index: [llms.txt]() Data updated: 2026-04-22T05:21:28.943Z Authors: Ligen Shi, Jun Qiu, Yuhang Zheng, Zengyu Pang, Chang Liu Published: 2026-04-03T08:04:30.000Z ## Abstract Fourier-encoded implicit neural representations (INRs) have shown strong capability in modeling continuous signals from discrete samples. However, conventional Fourier feature mappings use a fixed set of frequencies over the entire spatial domain, making them poorly suited to signals with spatially varying local spectra and often leading to slow convergence of high-frequency details. To address this issue, we propose an adaptive local frequency filtering method for Fourier-encoded INRs. The proposed method introduces a spatially varying parameter $\\alpha(\\mathbf{x})$ to modulate encoded Fourier components, enabling a smooth transition among low-pass, band-pass, and high-pass behaviors at different spatial locations. We further analyze the effect of the proposed filter from the neural tangent kernel (NTK) perspective and provide an NTK-inspired interpretation of how it reshapes the effective kernel spectrum. Experiments on 2D image fitting, 3D shape representation, and sparse data reconstruction demonstrate that the proposed method consistently improves reconstruction quality and leads to faster optimization compared with fixed-frequency baselines. In addition, the learned $\\alpha(\\mathbf{x})$ provides an intuitive visualization of spatially varying frequency preferences, which helps explain the behavior of the model on non-stationary signals. These results indicate that adaptive local frequency modulation is a practical enhancement for Fourier-encoded INRs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [2D image fitting on NTIRE 2017 (train)](): 2D Image Fitting; NTIRE 2017 (train); PSNR: 46.27. - [Signed Distance Field Representation on Stanford 3D Scanning Repository (Armadillo, Dragon, Lucy, Thai Statue)](): Signed Distance Field Representation; Stanford 3D Scanning Repository Armadillo, Dragon, Lucy, Thai Statue; Chamfer Distance (Armadillo): 0.00000108. ## Original sources and implementation [Original paper]() [PDF]()