Metraipolis › archive › dc_d9b4e2759c93

BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives — arXiv:2608.31113

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.31113
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:51.426Z
SHA-256 of the archived text
4a9ae96fcc037111d5faa63c620d41f2fcff7110cd64c8c1841c4ebbfc4cafb9
Stable URL of this page
https://metraipolis.com/documento/dc_d9b4e2759c93

How to cite

BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives — arXiv:2608.31113 — arXiv (en), https://arxiv.org/abs/2608.31113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9b4e2759c93 (Metraipolis archive dc_d9b4e2759c93, sha256 4a9ae96fcc037111d5faa63c620d41f2fcff7110cd64c8c1841c4ebbfc4cafb9)
BibTeX
@misc{dcd9b4e2759c93,
  title = {BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives — arXiv:2608.31113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.31113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9b4e2759c93; sha256 4a9ae96fcc037111d5faa63c620d41f2fcff7110cd64c8c1841c4ebbfc4cafb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.31113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and time-invariant vertex-to-component skinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages, skinning weights, or rig annotations. Our architecture conditions geometry-derived deformation latents on video features through factorized spatial-temporal attention, then decodes rigid transformations blended by predicted skinning weights. Trained with trajectory reconstruction, entropy regularization, and motion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.31113 — 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 2026-10-17T09:28:48.228Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).