Automatic Adjustment of Fourier Embedding Parametrizations for Implicit Neural Representations

Implicit neural representations parameterized by multilayer perceptrons have been shown to be a powerful paradigm that offers many potential advantages over traditional representations. The representation of fine details of signals is approached using a Fourier mapping to the input. However, naively applying a Fourier embedding is a double-edged sword, since gradient signals from the sampled points are incoherent (in terms of both direction and magnitude) and can easily cancel each other out. Hence, we propose an iterative algorithm that is able to gradually adjust a poorly chosen Fourier embedding in a way that it reaches an optimal parametrization after a few iterations.