Metraipolis › archive › dc_19371ede23d7

Dancing Stick Figures: An Introductory Dataset for Training Video Generation Models — arXiv:2608.29123

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29123
License (as archived)
CC0-1.0
Archived
2026-10-17T09:53:32.621Z
SHA-256 of the archived text
48d3c7bf3a102d3c658828cd11bba7b4688f253d4a213244e32061909c26a8c2
Stable URL of this page
https://metraipolis.com/documento/dc_19371ede23d7

How to cite

Dancing Stick Figures: An Introductory Dataset for Training Video Generation Models — arXiv:2608.29123 — arXiv (en), https://arxiv.org/abs/2608.29123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19371ede23d7 (Metraipolis archive dc_19371ede23d7, sha256 48d3c7bf3a102d3c658828cd11bba7b4688f253d4a213244e32061909c26a8c2)
BibTeX
@misc{dc19371ede23d7,
  title = {Dancing Stick Figures: An Introductory Dataset for Training Video Generation Models — arXiv:2608.29123},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29123},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19371ede23d7; sha256 48d3c7bf3a102d3c658828cd11bba7b4688f253d4a213244e32061909c26a8c2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Training a video-generation model from scratch is hard for reasons that precede model design. The feedback loop is long: a failure that appears only after a training run can make each attempted fix another run. The data are hard to reach: the corpora and recipes behind strong models are large, heterogeneous, and often unreleased. And scoring is blunt: open-ended generation has no single correct output, and an aggregate score does not by itself establish whether a sample succeeds or which property failed. Dancing Stick Figures is a synthetic video dataset built against these three obstacles. For iteration speed, its 64x64, 64-frame reference task is sized for practical repeated training on a single workstation GPU. For accessibility, the release is a 0.79-GB training tier of 4,020 video clips--1,340 six-second source motions, each rendered from three cameras by a deterministic dataset-generation harness--with checkpoints and a Colab workflow that reruns the reference training pipeline at reduced budget on a 16 GB Tesla T4. For scoring, every frame retains its generating state (ARDY cskel27 joint positions, camera, body parameters, and source motion) and per-pixel depth, surface normals, and part labels. These annotations support dataset-specific metrics for visible topology and part-wise motion; corruptions expose their sensitivities and blind spots.

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/2608.29123 — 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 2026-10-17T09:28:47.985Z 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).