Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PREF: Phasorial Embedding Fields for Compact Neural Representations

About

We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant border spectra than previous Fourier feature mapping or Positional Encoding. At the core is our compact 3D phasor volume where frequencies distribute uniformly along a 2D plane and dilate along a 1D axis. To this end, we develop a tailored and efficient Fourier transform that combines both Fast Fourier transform and local interpolation to accelerate na\"ive Fourier mapping. We also introduce a Parsvel regularizer that stables frequency-based learning. In these ways, Our PREF reduces the costly MLP in the frequency-based representation, thereby significantly closing the efficiency gap between it and other hybrid representations, and improving its interpretability. Comprehensive experiments demonstrate that our PREF is able to capture high-frequency details while remaining compact and robust, including 2D image generalization, 3D signed distance function regression and 5D neural radiance field reconstruction.

Binbin Huang, Xinhao Yan, Anpei Chen, Shenghua Gao, Jingyi Yu• 2022

Related benchmarks

TaskDatasetResultRank
Neural Radiance Field ReconstructionNeRF Synthetic (test)
Time18
12
Image PaintingText (test)
PSNR28.329
5
Image PaintingNatural (test)
PSNR24.113
5
SDF regressionArmadillo
IoU99.02
5
SDF regressionGargoyle
IOU99.05
5
Showing 5 of 5 rows

Other info

Follow for update