Metraipolis › archive › dc_f15ccadace2a
AESOP: Asymmetric Human-Camera Generation with Translation-Intensity Control — arXiv:2609.37229
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37229
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:41:04.616Z
- SHA-256 of the archived text
8fc797a6085d680d039e3dfd26a122f62852a3b3311323b04db1bcd4cc817baf- Stable URL of this page
https://metraipolis.com/documento/dc_f15ccadace2a
How to cite
AESOP: Asymmetric Human-Camera Generation with Translation-Intensity Control — arXiv:2609.37229 — arXiv (en), https://arxiv.org/abs/2609.37229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f15ccadace2a (Metraipolis archive dc_f15ccadace2a, sha256 8fc797a6085d680d039e3dfd26a122f62852a3b3311323b04db1bcd4cc817baf)
BibTeX
@misc{dcf15ccadace2a,
title = {AESOP: Asymmetric Human-Camera Generation with Translation-Intensity Control — arXiv:2609.37229},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37229},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f15ccadace2a; sha256 8fc797a6085d680d039e3dfd26a122f62852a3b3311323b04db1bcd4cc817baf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human motion defines an action, while a camera trajectory determines how it is presented. Camera generation for a given human motion and joint human-camera generation are usually treated as separate tasks, although both share an asymmetric dependency: human motion can be generated independently, whereas the camera responds to the realized action. We introduce AESOP, a unified framework with an independent human pathway and a shared human-conditioned camera generator. Its asymmetric architecture serves both tasks while preserving the human output during camera generation. Although human context anchors the shot to the action and camera text describes its movement, translation intensity remains underspecified. We therefore construct trajectory pairs that differ in camera translation magnitude while sharing human motion and camera text, then use these pairs to learn an explicit intensity condition. Experiments on the PulpMotion dataset demonstrate strong camera distributional and framing quality in both tasks and effective control over camera translation intensity. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.37229 — 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 2026-10-07T18:04:24.839Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).