Metraipolis › archive › dc_dc2abd56a8d2
Naturalness-guided Manifold Flow Matching for Sign Language Production — arXiv:2609.33339
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33339
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:56:41.514Z
- SHA-256 of the archived text
f5c0a7dad8aa4ce6766446ae2076532dbc0010bf98b007d22e3202668b632ddc- Stable URL of this page
https://metraipolis.com/documento/dc_dc2abd56a8d2
How to cite
Naturalness-guided Manifold Flow Matching for Sign Language Production — arXiv:2609.33339 — arXiv (en), https://arxiv.org/abs/2609.33339 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc2abd56a8d2 (Metraipolis archive dc_dc2abd56a8d2, sha256 f5c0a7dad8aa4ce6766446ae2076532dbc0010bf98b007d22e3202668b632ddc)
BibTeX
@misc{dcdc2abd56a8d2,
title = {Naturalness-guided Manifold Flow Matching for Sign Language Production — arXiv:2609.33339},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33339},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc2abd56a8d2; sha256 f5c0a7dad8aa4ce6766446ae2076532dbc0010bf98b007d22e3202668b632ddc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33339. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sign Language Production (SLP) aims to generate sign motions from text. Conditional Flow Matching methods have achieved strong performance in SLP by constructing conditional paths that transform a source distribution into a target distribution. However, existing methods construct these paths via linear interpolation, whereas the rotational geometry of human joints confines valid joint rotations to a manifold embedded in Euclidean space. Consequently, linear interpolation between two sign motions leaves this manifold and ignores the motion distribution on it. In this paper, we revisit SLP from the perspective of manifold transport and propose a Naturalness-guided Manifold Flow Matching framework, termed \textbf{SignNMFlow}, which constructs conditional paths directly on the motion manifold by jointly considering geometric efficiency and the motion distribution. Specifically, we exploit the intrinsic geometry of the manifold and introduce a motion naturalness measure to characterize the motion distribution. By minimizing the kinetic energy under this measure, we learn a naturalness-guided interpolation that couples a closed-form geodesic, which provides geometrically efficient transport, with a learnable deviation that incorporates the motion distribution, thereby significantly improving the fidelity of generated sign motions. Extensive qualitative and quantitative evaluations demonstrate the effectiveness of this work.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.33339 — 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 2026-10-07T20:29:01.223Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).