Metraipolis › archive › dc_ff6a642e271f
Video2SwimFish: An Automated Pipeline for Reconstructing Controllable Fish Models and Biological Locomotion from Real Fish Videos — arXiv:2609.38966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T15:11:48.062Z
- SHA-256 of the archived text
601d0405c4af0ad0f4128143f45ec951834585aae72628269751042e93bf7d92- Stable URL of this page
https://metraipolis.com/documento/dc_ff6a642e271f
How to cite
Video2SwimFish: An Automated Pipeline for Reconstructing Controllable Fish Models and Biological Locomotion from Real Fish Videos — arXiv:2609.38966 — arXiv (en), https://arxiv.org/abs/2609.38966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff6a642e271f (Metraipolis archive dc_ff6a642e271f, sha256 601d0405c4af0ad0f4128143f45ec951834585aae72628269751042e93bf7d92)
BibTeX
@misc{dcff6a642e271f,
title = {Video2SwimFish: An Automated Pipeline for Reconstructing Controllable Fish Models and Biological Locomotion from Real Fish Videos — arXiv:2609.38966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff6a642e271f; sha256 601d0405c4af0ad0f4128143f45ec951834585aae72628269751042e93bf7d92},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present Video2SwimFish, an automated pipeline and benchmark for building controllable fish assets from real-fish videos for underwater embodied AI. Given synchronized multi-view videos of an individual fish, the pipeline reconstructs a metrically scaled deformable mesh from a VLM-selected canonical frame, generates internal articulation adapted to that individual's morphology through a VLM actor-critic loop, and extracts a Biological Locomotion Manifold (BLM) from the fish's observed midline curvature. The BLM provides a low-dimensional action space bounded by real-fish motion, enabling an individual swimming policy to be learned for each reconstructed fish. We release two paired datasets: synchronized top- and front-view recordings of 120 individual fish across 6 species, and the controllable assets and individual swimming policies derived from them. Because every asset is tied to the animal it came from, the dataset supports a benchmark that evaluates locomotion learning not only on task success but on fidelity to that individual in trajectory shape, body curvature, and tail-beat frequency, across trajectory following, reward-free swimming behavior transfer from video, and a downstream case study in which a simulated BlueROV underwater robot captures one of the assets. We find that task success and locomotion fidelity do not necessarily improve together: the method achieving the highest task completion is not the method achieving the highest locomotion fidelity, and we identify faithful reproduction of individual animal locomotion as an open challenge for the community. Project website: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.38966 — 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 2026-10-07T14:44:47.396Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).