AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, Ren Ng

NeurIPS 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 2D image NaturalPSNR: 19.32 -> 25.57Improved
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 2D image TextPSNR: 18.40 -> 30.47Improved
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 3D shapeIoU: 0.864 -> 0.973Improved
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 2D CT Shepp-LoganPSNR: 16.75 -> 28.33Improved
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 2D CT ATLASPSNR: 15.44 -> 19.88Improved
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 3D MRI ATLASPSNR: 26.14 -> 34.51Improved
Add Gaussian Fourier features instead of no input mapping (ablation)Coordinate-based MLP · 3D NeRFPSNR: 22.41 -> 25.48Improved
Use Gaussian random features rather than positional encoding (ablation)Coordinate-based MLP · Across reported regression tasksPSNR or IoU: 24.95 -> 25.57; 27.57 -> 30.47; 0.960 -> 0.973; 26.89 -> 28.33; 19.55 -> 19.88; 32.23 -> 34.51; 25.28 -> 25.48Improved
Tune Fourier-feature frequency scale to match the target signal (ablation)Fourier-feature MLP · 1D function regressiontest errorMixed
Use more gradual Fourier-feature frequency falloff (lower p) (ablation)Fourier-feature MLP · 1D 1/f^1 noisetraining lossImproved
Use Gaussian isotropic frequencies rather than axis-aligned positional encoding (ablation)Coordinate-based MLP · 2D sinusoid images at varying anglesfit performanceImproved
Jointly optimize Fourier-feature parameters with network weights rather than keeping them fixed (ablation)Coordinate-based MLP · 2D image regressiontest performanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy