PaMO: Parallel Mesh Optimization for Intersection-Free
Low-Poly Modeling on the GPU

1 Yonsei University, 2 University of California San Diego, 3 Hillbot Inc.
* Equal contribution
teaser image.

We propose a GPU-based parallel mesh optimization that converts arbitrary meshes into low-poly, intersection-free, manifold meshes.
Our algorithm efficiently processes large-scale meshes, reducing 2M-face models to 2K-face in 2.29s and 7M-face models to 7K-face in 5.32s.

Abstract

Reducing the triangle count in complex 3D models is a basic geometry preprocessing step in graphics pipelines such as efficient rendering and interactive editing. However, most existing mesh simplification methods exhibit a few issues. Firstly, they often lead to self-intersections during decimation, a major issue for applications such as 3D printing and soft-body simulation. Second, to perform simplification on a mesh in the wild, one would first need to perform re-meshing, which often suffers from surface shifts and losses of sharp features. Finally, existing re-meshing and simplification methods can take minutes when processing large-scale meshes, limiting their applications in practice. To address the challenges, we introduce a novel GPU-based mesh optimization approach containing three key components: (1) a parallel re-meshing algorithm to turn meshes in the wild into watertight, manifold, and intersection-free ones, and reduce the prevalence of poorly shaped triangles; (2) a robust parallel simplification algorithm with intersection-free guarantees; (3) an optimization-based safe projection algorithm to realign the simplified mesh with the input, eliminating the surface shift introduced by re-meshing and recovering the original sharp features. The algorithm demonstrates remarkable efficiency, simplifying a 2-million-face mesh to 20k triangles in 3 seconds on RTX4090. We evaluated the approach on the Thingi10K dataset and showcased its exceptional performance in geometry preservation and speed.

Pipeline overview

pipeline image.

Comparison with Existing Works

pipeline image.

Our method guarantees intersection-free output meshes, whereas baseline models cannot avoid producing self-intersecting triangles (marked in red).

pipeline image.

The original shape is preserved better in our output mesh, with fewer spike artifacts.

Level of Detail

pipeline image.

Due to our parallelization and iterative simplification approach, we can achieve high-quality output meshes with level of detail in a reasonable time.

BibTeX

 TBD