Metraipolis › archive › dc_7f8cb7010b92
Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction — arXiv:2610.32250
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32250
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:51:49.163Z
- SHA-256 of the archived text
d7039bb3982b4cd8cf289079650dd147f52628b24d90cd1eb48e36a6c834c9b6- Stable URL of this page
https://metraipolis.com/documento/dc_7f8cb7010b92
How to cite
Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction — arXiv:2610.32250 — arXiv (en), https://arxiv.org/abs/2610.32250 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f8cb7010b92 (Metraipolis archive dc_7f8cb7010b92, sha256 d7039bb3982b4cd8cf289079650dd147f52628b24d90cd1eb48e36a6c834c9b6)
BibTeX
@misc{dc7f8cb7010b92,
title = {Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction — arXiv:2610.32250},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32250},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f8cb7010b92; sha256 d7039bb3982b4cd8cf289079650dd147f52628b24d90cd1eb48e36a6c834c9b6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32250. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle with fine-grained scene geometry and asset quality. Meanwhile, specialized 3D object generators provide detailed object geometry, while 3D foundation models offer strong and generalizable spatial understanding. We propose Easy-3Dfy, a compositional workflow that decouples object generation from scene layout estimation, allowing specialized models to fully exploit their respective strengths. An RPF-based aligner then bridges these capabilities by establishing geometric correspondence between object-local meshes and partial scene pointmaps, recovering object layout for scene composition. Without requiring complete scene-level supervision, the proposed workflow consistently outperforms SAM-3Dfy across multiple geometric metrics on Scene-Maker and 3D-FUTURE200. Our results demonstrate that explicit geometric composition can effectively combine high-quality object generation with strong spatial understanding, while enabling the workflow to benefit independently from advances in both 3D object generation and foundation models. 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/2610.32250 — 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 2026-10-26T19:45:33.400Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).