Generative Modeling with Orbit-Space Particle Flow Matching
ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-27
DOI: 10.1145/3811342 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Sinan Wang und 5 weiteren Autor:innen. Die Arbeit nennt 110 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.
Abstract (Originalsprache)
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; (ii) particles live in physical space, so the flow's 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 5× fewer steps and reaches airplane EMD comparable to DiT-3D with 26× fewer parameters and 5× fewer steps; and on single-shape encoding, where it produces normals and reconstructions competitive with 6D generators while operating entirely in 3D.
Förderung
- NSF
Zitieren
APA
Wang, S., He, J., Lu, S., Wang, R., Turk, G., & Zhu, B. (2026). Generative Modeling with Orbit-Space Particle Flow Matching. ACM Transactions on Graphics, 45(4), 1-27. https://doi.org/10.1145/3811342
Vancouver
Wang S, He J, Lu S, Wang R, Turk G, Zhu B. Generative Modeling with Orbit-Space Particle Flow Matching. ACM Transactions on Graphics. 2026;45(4):1-27. doi:10.1145/3811342
BibTeX
@article{Wang2026,
author = {Wang, Sinan and He, Jinjin and Lu, Shenyifan and Wang, Ruicheng and Turk, Greg and Zhu, Bo},
title = {Generative Modeling with Orbit-Space Particle Flow Matching},
journal = {ACM Transactions on Graphics},
year = {2026},
volume = {45},
number = {4},
pages = {1--27},
doi = {10.1145/3811342}
}
EUVIMED