Metraipolis › archive › dc_ee02a541882d
RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction — arXiv:2610.28351
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.28351
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:08:25.714Z
- SHA-256 of the archived text
879fe2555d8557d351cdbd6e9970a7d88f4694068adac8a58dea7259cee884b7- Stable URL of this page
https://metraipolis.com/documento/dc_ee02a541882d
How to cite
RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction — arXiv:2610.28351 — arXiv (en), https://arxiv.org/abs/2610.28351 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee02a541882d (Metraipolis archive dc_ee02a541882d, sha256 879fe2555d8557d351cdbd6e9970a7d88f4694068adac8a58dea7259cee884b7)
BibTeX
@misc{dcee02a541882d,
title = {RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction — arXiv:2610.28351},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.28351},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee02a541882d; sha256 879fe2555d8557d351cdbd6e9970a7d88f4694068adac8a58dea7259cee884b7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28351. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reconstructing dynamic 3D scenes from monocular video requires inferring motion from noisy and intermittently visible observations. Long-range tracks provide valuable geometric constraints, but integrating their fragmented temporal coverage into shared, continuous motion remains challenging. We introduce \textbf{RayCo4D}, a ray-conditioned continuous motion model for monocular 4D reconstruction that explicitly separates visual measurements from latent 3D motion states. Each track is associated with a reference-time 3D query constrained to its camera ray, and its image and depth observations constrain shared latent motion nodes through local many-to-many associations. Each node maintains an $\mathrm{SE}(3)$ pose and body-frame velocity at sparse support times. A white-noise-on-acceleration process prior couples neighboring states and defines continuous-time interpolation, allowing observations across visibility intervals to jointly constrain the same latent state this http URL inferred shared motion is transferred to Gaussian primitives through dual-quaternion blending, while reference-anchored local $\mathrm{SE}(3)$ residuals capture fine-scale non-rigid deformation beyond the shared scaffold. Experiments on diverse monocular dynamic scenes show that RayCo4D achieves competitive novel-view synthesis quality, improves structural and temporal consistency under rapid motion and incomplete tracks, and supports continuous-time rendering.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.28351 — 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 2026-10-21T07:05:43.643Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).