Metraipolis › archive › dc_30bef5025eb5

Hierarchical Flow Matching for 3D Point Cloud Generation — arXiv:2608.05557

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05557
License (as archived)
CC0-1.0
Archived
2026-10-31T10:35:57.198Z
SHA-256 of the archived text
9624c20ff9b25744d7b30f51ad6b447f67b76bd45f6f84728c0a1a19f1f00900
Stable URL of this page
https://metraipolis.com/documento/dc_30bef5025eb5

How to cite

Hierarchical Flow Matching for 3D Point Cloud Generation — arXiv:2608.05557 — arXiv (en), https://arxiv.org/abs/2608.05557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30bef5025eb5 (Metraipolis archive dc_30bef5025eb5, sha256 9624c20ff9b25744d7b30f51ad6b447f67b76bd45f6f84728c0a1a19f1f00900)
BibTeX
@misc{dc30bef5025eb5,
  title = {Hierarchical Flow Matching for 3D Point Cloud Generation — arXiv:2608.05557},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05557},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30bef5025eb5; sha256 9624c20ff9b25744d7b30f51ad6b447f67b76bd45f6f84728c0a1a19f1f00900},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating high-quality 3D point clouds requires capturing both global shape topology and local geometric details. Existing flow-based methods rely on continuous normalizing flows (CNFs) that demand expensive ODE solving and trace estimation during training, while diffusion models require hundreds of iterative denoising steps. Moreover, most approaches adopt single-level generation directly in point space, disregarding the hierarchical structure natural to 3D shapes. We propose Hierarchical Flow Matching (HFM) that extends flow matching to bilevel structure for unconditional 3D point cloud generation. HFM decomposes the task into two levels via optimal-transport flow matching: a \textit{Latent Flow Matching} models the global shape manifold in a compact latent space, and a \textit{Conditional Point Flow Matching} reconstructs detailed point clouds conditioned on the latent code. Both flows are trained with simple MSE regression losses. The resulting straight OT paths enable efficient sampling with as few as 15 Euler steps per flow, while the structured latent space supports downstream tasks including classification. Extensive experiments on ShapeNet and ModelNet benchmarks demonstrate that HFM achieves competitive or even best performance compared with prior state-of-the-art methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05557 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:23:30.980Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).