Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences

TL;DR

Neu-PiG introduces a novel preconditioned latent-grid encoding for fast, drift-free, and high-fidelity dynamic surface reconstruction from long sequences of point cloud data, outperforming existing methods in speed and accuracy.

Contribution

The paper proposes Neu-PiG, a new deformation optimization method using a preconditioned latent-grid encoding that enables rapid, drift-free surface reconstruction without explicit correspondences.

Findings

Neu-PiG achieves at least 60x faster training than state-of-the-art methods.

It provides superior accuracy and scalability for long sequence surface reconstructions.

Neu-PiG runs at inference speeds comparable to heavy pretrained models.

Abstract

Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, risking drift and requiring long runtimes, or rely on complex learned models that demand category-specific training. We present Neu-PiG, a fast deformation optimization method based on a novel preconditioned latent-grid encoding that distributes spatial features parameterized on the position and normal direction of a keyframe surface. Our method encodes entire deformations across all time steps at various spatial scales into a multi-resolution latent grid, parameterized by the position and normal direction of a reference surface from a single keyframe. This latent representation is then augmented for time modulation and decoded into per-frame 6-DoF deformations via a lightweight multilayer perceptron (MLP). To achieve high-fidelity, drift-free surface reconstructions in seconds, we employ Sobolev preconditioning during gradient-based training of the latent space, completely avoiding the need for any explicit correspondences or further priors. Experiments across diverse human and animal datasets demonstrate that Neu-PiG outperforms state-the-art approaches, offering both superior accuracy and scalability to long sequences while running at least 60x faster than existing training-free methods and achieving inference speeds on the same order as heavy pretrained models.