NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds

TL;DR

NumGrad-Pull introduces a tri-plane based method utilizing numerical gradients and progressive expansion to improve surface reconstruction from point clouds, achieving faster convergence and higher detail fidelity.

Contribution

It proposes a novel tri-plane representation with numerical gradients and a progressive expansion strategy to enhance surface reconstruction from point clouds.

Findings

Faster convergence of signed distance functions.

Improved local detail in reconstructed surfaces.

Robustness across various benchmarks.

Abstract

Reconstructing continuous surfaces from unoriented and unordered 3D points is a fundamental challenge in computer vision and graphics. Recent advancements address this problem by training neural signed distance functions to pull 3D location queries to their closest points on a surface, following the predicted signed distances and the analytical gradients computed by the network. In this paper, we introduce NumGrad-Pull, leveraging the representation capability of tri-plane structures to accelerate the learning of signed distance functions and enhance the fidelity of local details in surface reconstruction. To further improve the training stability of grid-based tri-planes, we propose to exploit numerical gradients, replacing conventional analytical computations. Additionally, we present a progressive plane expansion strategy to facilitate faster signed distance function convergence and design a data sampling strategy to mitigate reconstruction artifacts. Our extensive experiments across a variety of benchmarks demonstrate the effectiveness and robustness of our approach. Code is available at https://github.com/CuiRuikai/NumGrad-Pull