Metraipolis › archive › dc_b892c38bb7d0

TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos — arXiv:2609.38347

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38347
License (as archived)
CC0-1.0
Archived
2026-10-07T14:45:13.103Z
SHA-256 of the archived text
335ed31f781a5b5c3b20715663a809c4172654210a9362f39cef521dde753a11
Stable URL of this page
https://metraipolis.com/documento/dc_b892c38bb7d0

How to cite

TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos — arXiv:2609.38347 — arXiv (en), https://arxiv.org/abs/2609.38347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b892c38bb7d0 (Metraipolis archive dc_b892c38bb7d0, sha256 335ed31f781a5b5c3b20715663a809c4172654210a9362f39cef521dde753a11)
BibTeX
@misc{dcb892c38bb7d0,
  title = {TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos — arXiv:2609.38347},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38347},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b892c38bb7d0; sha256 335ed31f781a5b5c3b20715663a809c4172654210a9362f39cef521dde753a11},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantifying collective fish behavior requires accurate trajectories, yet multi-view 3D tracking remains challenging due to frequent occlusions, visually similar individuals, and the long-standing scarcity of identity annotations. We present TrackFish3D, a geometry-driven self-supervised framework for dense multi-camera 3D tracking of schooling fish. Instead of relying on appearance-based re-identification or manually annotated identities, TrackFish3D turns calibrated multi-view geometry into supervision: triangulation and reprojection consistency provide pseudo-associations, while a geometric encoder and global association transformer learn all-to-all cross-view correspondence within each frame. To make these associations identity-aware, TrackFish3D introduces a self-supervised contrastive objective that separates co-visible individuals in the embedding space, together with a temporal predictor that preserves identities and bridges short occlusions across frames. The resulting model is trained once on unlabeled footage and applied directly to unseen test videos, requiring no cross-view identity labels, temporal annotations, 3D ground truth, appearance features, or test-time optimization. On our benchmark, TrackFish3D improves 3D Multi-Object Tracking Accuracy from 87.7% for the strongest baseline to 95.8%. On the 3D-ZeF zebrafish benchmark, it achieves 81.1% MOTA, compared with 77.4% for the best geometric baseline. TrackFish3D also generalizes beyond fish, achieving strong results on real-world bird tracking.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.38347 — 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 2026-10-07T14:19:00.541Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).