JA-SIREN derives deterministic weights for two-layer sinusoidal MLPs via DST and Jacobi-Anger expansion to match target spectra, yielding 67.18 dB PSNR on Kodak with zero variance.
FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Existing periodic activation-based implicit neural representation (INR) networks, such as SIREN and FINER, suffer from hidden feature redundancy, where neurons within a layer capture overlapping frequency components due to the use of a fixed frequency multiplier. This redundancy limits the expressive capacity of multilayer perceptrons (MLPs). Drawing inspiration from classical signal processing methods such as the Discrete Sine Transform (DST), in this paper, we propose FM-SIREN and FM-FINER, which assign Nyquist-informed, neuron-specific frequency multipliers to periodic activations. Contrary to existing approaches, our design introduces frequency diversity without requiring hyperparameter tuning or additional network depth. This simple yet principled approach reduces the redundancy of features by nearly 50% and consistently improves signal reconstruction across diverse INR tasks, such as fitting 1D audio, 2D image and 3D shape, and video, outperforming their baseline counterparts while maintaining efficiency.
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
FiRe adds a low-rank gating path to periodic INRs to reparameterize per-neuron frequencies as an NTK-based preconditioner, yielding up to +1 dB PSNR gains over parameter-matched baselines at short training budgets.
citing papers explorer
-
JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching
JA-SIREN derives deterministic weights for two-layer sinusoidal MLPs via DST and Jacobi-Anger expansion to match target spectra, yielding 67.18 dB PSNR on Kodak with zero variance.
-
FiRe: Frequency Reparameterization as a Preconditioner for Periodic Implicit Neural Representations
FiRe adds a low-rank gating path to periodic INRs to reparameterize per-neuron frequencies as an NTK-based preconditioner, yielding up to +1 dB PSNR gains over parameter-matched baselines at short training budgets.