Different from existing works that represent deformation fields by training a general-purpose neural network, we advocate for an approximation based on mesh-free methods. By letting the network learn deformation parameters at a sparse set of positions in space (nodes), we reconstruct the continuous deformation field in a closed-form with guaranteed smoothness.

Transformers have shown great power in time series forecasting due to their global-range modeling ability.

This space-bending geometry makes the equivariance to translations of convolutional networks an undesired inductive bias.