1 LearnableFourierFeaturesConfig

vin.pose_encoding.LearnableFourierFeaturesConfig()

Config-as-factory wrapper for LearnableFourierFeatures.

1.1 Attributes

Name	Description
input_dim	Input dimensionality (default: 6 for SE(3) relative pose as translation + so(3) log).
fourier_dim	Fourier feature dimensionality (must be even).
hidden_dim	Hidden dimension of the internal MLP.
output_dim	Output positional encoding dimensionality (per input vector).
gamma	Initialization scale (paper parameter \(\gamma\)).
include_input	Concatenate raw inputs to the learned encoding when True.