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

2025-09-06

AI Summary

To address critical challenges in complex 3D mesh simplification—including self-intersections, loss of sharp features, surface deviation, and low computational efficiency—this paper introduces the first end-to-end simplification framework that supports parallel remeshing and provides theoretical guarantees of intersection-free output. Our method integrates GPU-accelerated parallel remeshing, a robust topology-preserving simplification algorithm, and an optimization-based safe projection strategy. It processes arbitrary input meshes directly—without preprocessing—while preventing surface deviation and faithfully recovering sharp features. On an RTX 4090, it simplifies a 2-million-face mesh to 20,000 triangles in just three seconds. Evaluated on the Thingi10K dataset, our approach significantly outperforms state-of-the-art methods in geometric fidelity, strict intersection-freeness, and throughput—achieving millisecond-level processing per mesh.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning on the Edge & Model Compression
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

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.

Problem

• Reducing triangle count without self-intersections in 3D models
• Eliminating surface shifts and sharp feature loss during remeshing
• Accelerating large-scale mesh processing through GPU parallelization

Innovation

• Parallel re-meshing for watertight, manifold meshes
• Robust parallel simplification with intersection-free guarantee
• Optimization-based projection to realign and recover features