PREF: Phasorial Embedding Fields for Compact Neural Representations
This work addresses efficiency and interpretability issues in neural representations for computer vision and graphics, though it appears incremental as it builds on existing frequency-based methods.
The paper tackles the problem of inefficient frequency-based neural representations by introducing PREF, a compact phasorial embedding field that reduces the MLP size and accelerates training, achieving high-frequency detail capture in tasks like 3D SDF regression and 5D NeRF reconstruction.
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 naïve 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.