可学习频谱激活函数 LSA：改进隐式神经表示的重建质量

View PDF HTML (experimental)

Abstract:Implicit neural representations (INRs) are shaped by the spectral structure induced by their input encodings and activation functions. Existing methods improve fitting primarily by modifying which frequencies are available to the network, through coordinate encodings or periodic nonlinearities. However, frequency access is not the only bottleneck: signals with localized or spatially varying structure require the network to efficiently compose frequencies into multi-harmonic internal responses. We introduce learnable spectral activations (LSA), which replace fixed neuron-level nonlinearities with a residual truncated Fourier series whose harmonic amplitudes are learned during training. LSA does not expand the asymptotic function class. Instead, it changes the factorization of the representation: linear weights select features while activation coefficients control spectral shaping, and the two are updated by separate gradients. Because the activation output is affine in the coefficients given fixed pre-activations, spectral tuning becomes a more direct subproblem compared to architectures where it is entangled with feature selection. Empirically, this factorization concentrates more target-signal energy in the leading eigenmodes of the neural tangent kernel, consistent with improved optimization behavior. Across audio, image, neural radiance field, and neural acoustic field tasks, LSA also improves reconstruction quality.

Subjects:	Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2610.07419 [cs.LG]
	(or arXiv:2610.07419v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.07419 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tamir Shor [view email]
[v1] Mon, 5 Oct 2026 21:29:04 UTC (15,260 KB)