EUVIMEDEUVIMED entdecken
Crossref

Spatial-Frequency-Aware Implicit Neural Representation of Multidimensional Signals via MLP-KAN Fusion

Wen Yan, Ligen Shi, Jun Qiu, Haimiao Zhang, Lina Wu, Chang Liu

IEEE Transactions on Image Processing · 2026 · 1-1

DOI: 10.1109/tip.2026.3750876 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Wen Yan und 5 weiteren Autor:innen. Gefördert von: National Natural Science Foundation of China, Postdoctoral Research Fund of Inner Mongolia University, Natural Science Foundation of Inner Mongolia Autonomous Region.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Implicit Neural Representations (INRs) have emerged as a compelling paradigm for modeling multidimensional signals by mapping continuous coordinates to signal values. However, Multi-Layer Perceptrons (MLP)-based INRs inherently suffer from spectral bias, which favors low-frequency components and suppresses the reconstruction of essential high-frequency details. While existing techniques, such as Fourier feature mappings, mitigate this issue, they often rely on sensitive manual tuning and are prone to spectral artifacts. In this paper, we propose a spatial-frequency-aware INR framework that combines an MLP branch with a Kolmogorov-Arnold network (KAN) branch for complementary frequency-oriented modeling. The MLP branch provides a low-frequency-oriented representation of smooth structures, whereas the KAN branch complements localized variations and fine details. To coordinate the two branches, we integrate the discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT) into the output fusion stage. The outputs of the two branches are decomposed into wavelet coefficients, and the corresponding coefficients are additively fused before inverse wavelet reconstruction. A wavelet-domain band-separation regularization further penalizes high-frequency responses in the MLP branch and low-frequency responses in the KAN branch, thereby encouraging complementary frequency-oriented behavior. Experiments on 1D signals, 2D images, 3D volumes and signed distance functions, videos, and 4D light-fields demonstrate the applicability of the proposed representation across the evaluated signal modalities. Results demonstrate improved reconstruction fidelity across the evaluated signal modalities.

Förderung

  • National Natural Science Foundation of China
  • Postdoctoral Research Fund of Inner Mongolia University
  • Natural Science Foundation of Inner Mongolia Autonomous Region

Zitieren

APA

Yan, W., Shi, L., Qiu, J., Zhang, H., Wu, L., & Liu, C. (2026). Spatial-Frequency-Aware Implicit Neural Representation of Multidimensional Signals via MLP-KAN Fusion. IEEE Transactions on Image Processing, 1-1. https://doi.org/10.1109/tip.2026.3750876

Vancouver

Yan W, Shi L, Qiu J, Zhang H, Wu L, Liu C. Spatial-Frequency-Aware Implicit Neural Representation of Multidimensional Signals via MLP-KAN Fusion. IEEE Transactions on Image Processing. 2026:1-1. doi:10.1109/tip.2026.3750876

BibTeX
@article{Yan2026,
  author = {Yan, Wen and Shi, Ligen and Qiu, Jun and Zhang, Haimiao and Wu, Lina and Liu, Chang},
  title = {Spatial-Frequency-Aware Implicit Neural Representation of Multidimensional Signals via MLP-KAN Fusion},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  pages = {1--1},
  doi = {10.1109/tip.2026.3750876}
}
Kostenlos starten →