Metraipolis › archive › dc_ca65ba7078a7
CoLa3D: Composable Latent 3D Decomposition — arXiv:2611.03533
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03533
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:56:39.084Z
- SHA-256 of the archived text
2007899a77efec1264b66aaeae03a47ca996143dcdaf7b9b3663e716dcf50ec5- Stable URL of this page
https://metraipolis.com/documento/dc_ca65ba7078a7
How to cite
CoLa3D: Composable Latent 3D Decomposition — arXiv:2611.03533 — arXiv (en), https://arxiv.org/abs/2611.03533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca65ba7078a7 (Metraipolis archive dc_ca65ba7078a7, sha256 2007899a77efec1264b66aaeae03a47ca996143dcdaf7b9b3663e716dcf50ec5)
BibTeX
@misc{dcca65ba7078a7,
title = {CoLa3D: Composable Latent 3D Decomposition — arXiv:2611.03533},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03533},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca65ba7078a7; sha256 2007899a77efec1264b66aaeae03a47ca996143dcdaf7b9b3663e716dcf50ec5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce CoLa3D, a simple and effective model for composable 3D scene decomposition that, given a single whole-scene latent from either a single image or an existing scene mesh as input, directly outputs a set of object meshes with consistent spatial layout that can be assembled back into a coherent scene. CoLa3D introduces a novel paradigm for 3D scene decomposition within a shared whole-scene latent, unlike alternatives that perform per-object generation in canonical spaces and then glue the objects back together with fragile pose and scale estimation. The network is a lightweight, flexible, and scalable query-based transformer that accepts various types of queries, including 2D masks, 3D points, and learnable queries, and learns to decompose the scene into objects in a compact latent space. On both synthetic and real-world datasets, CoLa3D achieves state-of-the-art performance on composable 3D scene decomposition, substantially improving global scene-level consistency and object-level quality while running 2 times faster and using less than 1% of SAM 3D's training data. Visible depth on par with MoGe2 further confirms that latent decomposition preserves accurate visible scene geometry while producing physically complete, decomposable object meshes. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.03533 — 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 2026-11-03T18:16:53.081Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).