REVIEW 15 cited by
Implicit Neural Representations with Periodic Activation Functions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations. We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or Sirens, are ideally suited for representing complex natural signals and their derivatives. We analyze Siren activation statistics to propose a principled initialization scheme and demonstrate the representation of images, wavefields, video, sound, and their derivatives. Further, we show how Sirens can be leveraged to solve challenging boundary value problems, such as particular Eikonal equations (yielding signed distance functions), the Poisson equation, and the Helmholtz and wave equations. Lastly, we combine Sirens with hypernetworks to learn priors over the space of Siren functions.
Forward citations
Cited by 15 Pith papers
-
Cosmo-SPINN: Fuzzy Dark Matter Simulations with Physics-Informed Generative Networks
Physics-informed generative U-Nets evolve and super-resolve fuzzy dark matter fields under Schrödinger–Poisson constraints with far less supervised data than pure data-driven baselines.
-
Fast, accurate, and differentiable: a neural-network surrogate for NRSur7dq4 precessing binary black hole waveforms
A piecewise MLP surrogate emulates NRSur7dq4 over its full domain at NR-faithful accuracy with ~1 ms GPU latency and a fully differentiable JAX likelihood pipeline.
-
From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric Data
Time-varying volumes are compressed by mapping each spatial coordinate directly to its full temporal sequence, using mixture-of-experts routing and low-rank decoders.
-
PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping
A self-supervised, physics-regularized neural reconstruction produces high-resolution fetal brain T2 maps at 0.55 T and 1.5 T from multi-echo MRI, with reduced acquisition time.
-
Chebyshev Manifold Adaptation
ChebyMA uses Chebyshev polynomial surfaces to parameterize weight updates, claiming a better parameter-accuracy trade-off than LoRA, TLoRA, and StelLA on CIFAR and text classification.
-
Exterior complex scaling enables physics-informed neural networks for quantum scattering
Exterior complex scaling turns oscillatory scattering waves into decaying waves, letting physics-informed neural networks solve nuclear scattering benchmarks.
-
Deformable Medical Image Registration with KAN-based Implicit Neural Representations
KAN-based implicit neural networks with randomized basis sampling outperform existing INR registration methods on three medical imaging datasets at lower computational cost.
-
Physics-Guided Dual Implicit Neural Representations for Source Separation
A dual implicit neural network with a physics-guided convolution kernel separates single-magnon signals from heterogeneous background in 4D neutron scattering data without labels.
-
Brain-wide interpolation and conditioning of gene expression in the human brain using Implicit Neural Representations
An implicit neural representation with a gene-similarity axis interpolates sparse brain gene expression into voxel-level maps that match abagen and correlate with tau-PET.
-
SPINN: Advancing Cosmological Simulations of Fuzzy Dark Matter with Physics Informed Neural Networks
A physics-informed neural network (SPINN) solves the Schrödinger-Poisson equations for fuzzy dark matter collapse in 1D and 3D, matching a spectral solver on a sinusoidal test case.
-
Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization
SNIP's symbolic-numeric alignment stays coarse and does not improve during optimization, so multi-modal LSO does not yet deliver effective bi-modal search for symbolic regression.
-
Generative Latent Diffusion Model for Inverse Modeling and Uncertainty Analysis in Geological Carbon Sequestration
A conditional neural field plus latent diffusion model jointly generates geological models and flow responses, enabling zero-shot Bayesian inversion for CO2 storage.
-
Assessing Learned Models for Phase-only Hologram Compression
A small SIREN implicit neural representation compresses phase-only holograms to about 40% of their size with a reconstructed 3D PSNR of 34.54 dB, while an off-the-shelf image VAE fails.
-
Low-Rank Augmented Implicit Neural Representation for Unsupervised High-Dimensional Quantitative MRI Reconstruction
LoREIN couples implicit neural representations with low-rank temporal subspace modeling to reconstruct quantitative MRI maps and weighted images directly from undersampled k-space.
-
Super-temporal-resolution Photoacoustic Imaging with Dynamic Reconstruction through Implicit Neural Representation in Sparse-view
An INR-based unsupervised method reconstructs sparse-view dynamic photoacoustic images and performs 4x temporal frame interpolation using only spatiotemporal coordinates.
Discussion (0). Sign in to comment.