Metraipolis › archive › dc_a6fa0f090a4e
Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation — arXiv:2609.06218
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06218
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:06:53.171Z
- SHA-256 of the archived text
38accb9cb6b5beaafb831ee9c40f2a248ac197f468a6bb1825f0397f783a723e- Stable URL of this page
https://metraipolis.com/documento/dc_a6fa0f090a4e
How to cite
Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation — arXiv:2609.06218 — arXiv (en), https://arxiv.org/abs/2609.06218 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6fa0f090a4e (Metraipolis archive dc_a6fa0f090a4e, sha256 38accb9cb6b5beaafb831ee9c40f2a248ac197f468a6bb1825f0397f783a723e)
BibTeX
@misc{dca6fa0f090a4e,
title = {Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation — arXiv:2609.06218},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06218},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6fa0f090a4e; sha256 38accb9cb6b5beaafb831ee9c40f2a248ac197f468a6bb1825f0397f783a723e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06218. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch structures into token sequences and do not use test-time computation effectively. We study these choices within a unified autoregressive framework. First, we introduce branch-centric tokenization, a branch-aware representation that places structurally related elements next to each other and encodes connectivity directly in the sequence. Compared with standard BFS-style serialization, this representation yields more compact sequences. Second, we introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh, maps all predictions back to a common frame, and selects the final skeleton based on mesh coverage and consistency among predictions from different views. Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods. In particular, our method reduces the CD-J2B error by 16.9% on the Articulation-XL2.0 dataset compared to the strongest directly comparable baseline, Auto-Connect. Qualitative results on in-the-wild meshes further demonstrate generalization across diverse inputs. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.06218 — 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 2026-10-16T14:49:57.058Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).