REVIEW 21 cited by
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
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
We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains. These results shed light on recent advances in computer vision and graphics that achieve state-of-the-art results by using MLPs to represent complex 3D objects and scenes. Using tools from the neural tangent kernel (NTK) literature, we show that a standard MLP fails to learn high frequencies both in theory and in practice. To overcome this spectral bias, we use a Fourier feature mapping to transform the effective NTK into a stationary kernel with a tunable bandwidth. We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities.
Forward citations
Cited by 21 Pith papers
-
Few-shot Deep Learning for Phase-Amplitude Aberration Correction in Transcranial Focused Ultrasound
A few-shot deep surrogate predicts CT-derived phase and amplitude corrections for a 96-element ultrasound array, matching time-reversal focus quality at roughly 2,500x speedup.
-
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.
-
LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression
A tokenizer-free pixel embedding, position encoding, and 256-way head let frozen LLMs act as portable entropy models for lossless RGB compression across model families.
-
Self-Supervised Implicit CEST Reconstruction via Physics-Informed Lorentz Encoding
Embedding learnable Lorentzian basis functions into the spectral encoding layer of an implicit neural representation enables high-fidelity CEST Z-spectrum reconstruction from as few as 21 frequency offsets.
-
Gradient Networks for Universal Magnetic Modeling of Synchronous Machines
A gradient-network model trained on sparse flux-linkage/current data reproduces the saturable, angle-periodic magnetic maps of a 5.6-kW synchronous machine while enforcing reciprocity, convexity, and smoothness by con...
-
A universal vision transformer for fast calorimeter simulations
A vision-transformer flow-matching model generates calorimeter showers across regular and irregular detector geometries at millisecond speeds, and pretraining plus fine-tuning cuts training cost by about half.
-
ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
ExtraGS combines Gaussian-SDF road surfaces, far-field Gaussians, and spherical-harmonics uncertainty gating to generate geometrically consistent extrapolated driving views.
-
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.
-
Learning 3D Hypersonic Flow with Physics-Enhanced Neural Fields: A Case Study on the Orion Reentry Capsule
A Fourier-enhanced neural field predicts steady 3D hypersonic flow around the Orion capsule in seconds, matching CFD snapshots at held-out angles of attack better than graph networks.
-
Spectral Embedding via Chebyshev Bases for Robust DeepONet Approximation
Replacing the coordinate-input trunk of a DeepONet with a fixed Chebyshev polynomial dictionary lowers reported reconstruction error on bounded non-periodic PDE benchmarks.
-
Combining complex Langevin dynamics with score-based and energy-based diffusion models
Energy-based diffusion models trained on complex Langevin data produce an explicit energy function for the sampled distribution, enabling MCMC without re-simulation.
-
Continuously Tempered Diffusion Samplers
CTDS trains neural samplers with a controlled Langevin dynamics over both position and a continuous temperature coordinate, and reports improved sampling on a 40-mode Gaussian mixture.
-
Physics-informed machine learning surrogate for scalable simulation of thermal histories during wire-arc directed energy deposition
A data-free physics-informed neural network matches finite-element thermal histories of wire-arc directed energy deposition to about 7% relative L2 error, reporting up to 98.6% compute-time reduction versus a fine-mes...
-
Operator-based machine learning framework for generalizable prediction of unsteady treatment dynamics in stormwater infrastructure
A composite operator neural network predicts 3D unsteady flow and particle concentrations in a stormwater separator, matching CFD closely on most held-out storm events.
-
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.
-
BlastOFormer: Attention and Neural Operator Deep Learning Methods for Explosive Blast Prediction
BlastOFormer, a transformer with signed-distance inputs and an auxiliary unscaling CNN, predicts full-field blast peak pressures with R2 up to 0.9516 in the unscaled domain and about 100,000x faster than blastFoam CFD.
-
Hybrid Adaptive Modeling in Process Monitoring: Leveraging Sequence Encoders and Physics-Informed Neural Networks
This paper introduces a physics-informed neural network that uses Deep Sets to encode sensor data, allowing one model to adapt to new parameters and boundary conditions without retraining, with tests on a chaotic ODE,...
-
Performance of Krotov, PRONTO and PINN for optimal control of quantum gates
An enhanced PINN with Fourier features, per-epoch normalization, and pretraining designs high-fidelity quantum gates comparable to Krotov and PRONTO, but more slowly and with overclaimed headline results.
-
DiffPR: Diffusion-Based Phase Reconstruction via Frequency-Decoupled Learning
DiffPR couples a quarter-resolution U-Net phase predictor with an unconditional diffusion refiner and reports solid but modest gains over U-Net baselines on four QPI datasets, with the claimed spectral-bias mechanism ...
-
Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization
Wavelet-based positional encodings are claimed to improve how transformers extrapolate to longer sequences, with a toy experiment supporting the claim but with weak theory.
Discussion (0). Sign in to comment.