NeuralSSD: A Neural Solver for Signed Distance Surface Reconstruction
This addresses the challenge of accurate and stable surface reconstruction for applications in computer vision and graphics, though it appears incremental by building on existing implicit methods.
The paper tackled the problem of reconstructing 3D implicit surfaces from point clouds by proposing NeuralSSD, a solver-based method that balances point cloud reliability and learns 3D information, achieving state-of-the-art results on datasets like ShapeNet and Matterport.
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.