| title | Generative Modeling with Orbit-Space Particle Flow Matching |
|---|---|
| authors | Sinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Turk, Bo Zhu |
| date | 2026-05-04 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.02222 |
| upvotes | 9 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP is motivated by two insights: (i) particles are defined up to permutation symmetries, so anonymous indexing inflates per-index target variance and yields curved, hard-to-learn flows; and (ii) particles live in physical space, so the flow terminal velocity has physical meaning and can encode geometric attributes, e.g., surface normals. OGPP instantiates three key components: (1) orbit-space canonicalization of the probability-path terminal endpoint, (2) particle index embeddings for role specialization, and (3) geometric probability paths with arc-length-aware terminal velocities that generate normals as a byproduct of the flow. We evaluate OGPP on minimal-surface benchmarks, where it reduces metric error by up to two orders of magnitude in a single inference step; on ShapeNet, where it matches the state of the art with 5x fewer steps and reaches airplane EMD comparable to DiT-3D with 26x fewer parameters and 5x fewer steps; and on single-shape encoding, where it produces normals and reconstructions competitive with 6D generators while operating entirely in 3D. |
cite
@misc{wang2026generative,
title={Generative Modeling with Orbit-Space Particle Flow Matching},
author={Sinan Wang and Jinjin He and Shenyifan Lu and Ruicheng Wang and Greg Turk and Bo Zhu},
year={2026},
eprint={2605.02222},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.02222}
}