Metraipolis › archive › dc_d00b783ab014

Point4D: Long-range 4D Motion Reconstruction — arXiv:2609.09145

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09145
License (as archived)
CC0-1.0
Archived
2026-10-16T15:12:34.505Z
SHA-256 of the archived text
7b9b2cc16ab02cd5066de6707eff0018ea19c67f7fa5d501cc6ddf0a91091ce2
Stable URL of this page
https://metraipolis.com/documento/dc_d00b783ab014

How to cite

Point4D: Long-range 4D Motion Reconstruction — arXiv:2609.09145 — arXiv (en), https://arxiv.org/abs/2609.09145 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d00b783ab014 (Metraipolis archive dc_d00b783ab014, sha256 7b9b2cc16ab02cd5066de6707eff0018ea19c67f7fa5d501cc6ddf0a91091ce2)
BibTeX
@misc{dcd00b783ab014,
  title = {Point4D: Long-range 4D Motion Reconstruction — arXiv:2609.09145},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09145},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d00b783ab014; sha256 7b9b2cc16ab02cd5066de6707eff0018ea19c67f7fa5d501cc6ddf0a91091ce2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09145. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Point4D, a feed-forward model for 4D reconstruction of long-range video sequences. Point4D is able to reliably infer dense per-point 3D trajectories across multi-hundred-frame videos, unlike existing 4D methods that are limited to short input windows of at most a few dozen frames. A key innovation that enables this is our flexible 3D query-based motion decoder that decouples trajectory prediction from image-plane visibility. The predicted 3D endpoints are then directly re-queried in the next chunk without re-projection or matching. Furthermore, we show that extracting and reusing a visual descriptor from an arbitrary frame where the point is visible leads to better performance than relying solely on the source patch. Overall, Point4D achieves state-of-the-art performance across diverse long-video tracking benchmarks spanning over 200 frames and largely outperforms previous feed-forward 4D method. Project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.09145 — 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 2026-10-16T14:49:57.398Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).