Metraipolis › archive › dc_b0e299bb4781

ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference — arXiv:2608.12232

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12232
License (as archived)
CC0-1.0
Archived
2026-10-19T05:49:43.489Z
SHA-256 of the archived text
e7bf7433c788b21879863890d08641f450bb4f2d49d90f60cd985e37b72ce771
Stable URL of this page
https://metraipolis.com/documento/dc_b0e299bb4781

How to cite

ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference — arXiv:2608.12232 — arXiv (en), https://arxiv.org/abs/2608.12232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b0e299bb4781 (Metraipolis archive dc_b0e299bb4781, sha256 e7bf7433c788b21879863890d08641f450bb4f2d49d90f60cd985e37b72ce771)
BibTeX
@misc{dcb0e299bb4781,
  title = {ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference — arXiv:2608.12232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b0e299bb4781; sha256 e7bf7433c788b21879863890d08641f450bb4f2d49d90f60cd985e37b72ce771},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geometry-aware video object scaling aims to anisotropically resize the object along object-centric axes while preserving geometric plausibility, temporal coherence, and background consistency. Existing text-guided methods mainly operate in the 2D image plane, while depth-guided approaches provide coarse control and mesh-based methods require costly 3D reconstruction. We present a progressive two-stage training framework that decouples geometry-aware foreground transformation from background preservation and realistic video composition, without mesh-pixel alignment and explicit 3D reconstruction at inference. In both stages, geometrically perturbed pseudo-sources are constructed from real videos, while the original complete videos are retained as reconstruction targets. The first stage uses planar transformations to learn robust foreground-background composition, whereas the second introduces object-centric 3D deformation guidance for geometry-aware scaling. This pseudo-source reconstruction formulation enables real-video synthesis without paired real-world scaling targets. We construct complementary paired-geometry and real-background benchmarks and further evaluate on in-the-wild videos. Extensive experiments demonstrate superior geometric consistency, foreground fidelity, and background preservation, together with faster and more practical inference than methods requiring explicit 3D reconstruction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12232 — 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 2026-10-19T05:42:25.923Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).