Diffusing Winding Gradients (DWG): A Parallel and Scalable Method for 3D Reconstruction from Unoriented Point Clouds

TL;DR

The paper introduces Diffusing Winding Gradients (DWG), a parallelizable method for efficient 3D surface reconstruction from unoriented point clouds, outperforming existing methods in speed and robustness.

Contribution

DWG is a novel approach that leverages gradient alignment of the GWN field for 3D reconstruction without solving linear systems, enabling scalable parallel implementation.

Findings

Achieves 30-120x faster reconstruction on large models using GPU.

Outperforms existing methods in runtime performance.

Demonstrates robustness to noise, outliers, and complex structures.

Abstract

This paper presents a new method, Diffusing Winding Gradients (DWG), for reconstructing watertight 3D surfaces from unoriented point clouds. Our method exploits the alignment between the gradients of the generalized winding number (GWN) field and globally consistent normals to orient points effectively. Starting with an unoriented point cloud, DWG initially assigns a random normal to each point. It computes the corresponding GWN field and extract a level set whose iso-value is the average GWN values across all input points. The gradients of this level set are then utilized to update the point normals. This cycle of recomputing the GWN field and updating point normals is repeated until the GWN level sets stabilize and their gradients cease to change. Unlike conventional methods, our method does not rely on solving linear systems or optimizing objective functions, which simplifies its implementation and enhances its suitability for efficient parallel execution. Experimental results demonstrate that our method significantly outperforms existing methods in terms of runtime performance. For large-scale models with 10 to 20 million points, our CUDA implementation on an NVIDIA GTX 4090 GPU achieves speeds 30-120 times faster than iPSR, the leading sequential method, tested on a high-end PC with an Intel i9 CPU. Additionally, by employing a screened variant of GWN, DWG demonstrates enhanced robustness against noise and outliers, and proves effective for models with thin structures and real-world inputs with overlapping and misaligned scans. For source code and more details, visit our project webpage: https://dwgtech.github.io/.