NeuralSSD: A Neural Solver for Signed Distance Surface Reconstruction

TL;DR

NeuralSSD introduces a neural solver based on the Galerkin method for high-quality 3D surface reconstruction from point clouds, improving accuracy and robustness over existing implicit methods.

Contribution

It presents a novel energy formulation and a specialized convolutional network to enhance the fit and stability of implicit surface reconstructions from point cloud data.

Findings

Achieves state-of-the-art accuracy on ShapeNet and Matterport datasets.

Demonstrates superior generalization and robustness in surface reconstruction.

Provides a stable and precise implicit surface fitting method.

Abstract

We proposed a generalized method, NeuralSSD, for reconstructing a 3D implicit surface from the widely-available point cloud data. NeuralSSD is a solver-based on the neural Galerkin method, aimed at reconstructing higher-quality and accurate surfaces from input point clouds. Implicit method is preferred due to its ability to accurately represent shapes and its robustness in handling topological changes. However, existing parameterizations of implicit fields lack explicit mechanisms to ensure a tight fit between the surface and input data. To address this, we propose a novel energy equation that balances the reliability of point cloud information. Additionally, we introduce a new convolutional network that learns three-dimensional information to achieve superior optimization results. This approach ensures that the reconstructed surface closely adheres to the raw input points and infers valuable inductive biases from point clouds, resulting in a highly accurate and stable surface reconstruction. NeuralSSD is evaluated on a variety of challenging datasets, including the ShapeNet and Matterport datasets, and achieves state-of-the-art results in terms of both surface reconstruction accuracy and generalizability.