Metraipolis › archive › dc_37dfdf78991a
CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes — arXiv:2609.36024
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36024
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:00.347Z
- SHA-256 of the archived text
f24af242e46c86a55ca835cbe3f9347c8d4bb447ce8e6b50146b2862ad9735b4- Stable URL of this page
https://metraipolis.com/documento/dc_37dfdf78991a
How to cite
CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes — arXiv:2609.36024 — arXiv (en), https://arxiv.org/abs/2609.36024 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37dfdf78991a (Metraipolis archive dc_37dfdf78991a, sha256 f24af242e46c86a55ca835cbe3f9347c8d4bb447ce8e6b50146b2862ad9735b4)
BibTeX
@misc{dc37dfdf78991a,
title = {CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes — arXiv:2609.36024},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36024},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37dfdf78991a; sha256 f24af242e46c86a55ca835cbe3f9347c8d4bb447ce8e6b50146b2862ad9735b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36024. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reconstructing simulation-ready 3D scenes from real-world observations enables robotics, gaming, and immersive applications, yet existing methods largely assume rigid objects. This leaves an important gap for deformables, whose simulation-ready geometry depends on dimensionality (curves, surfaces, or volumes) and whose behavior may require models beyond elasticity. We present CoDimRecon, an agentic framework that reconstructs editable scenes containing rigid, articulated, and deformable objects from multi-view RGB observations. Scene-level geometric priors ground scale and layout, while object-level generated meshes guide the agent toward detailed, compact geometry; articulated rigid objects are decomposed into movable parts with explicit joints. For deformables, category-wise agent sessions reconstruct curves as centerlines with radii, surfaces as manifold shells with thickness, and volumes as watertight solids for volumetric meshing. Reusable simulator skills initialize compatible physical models and parameters, while agent-guided behavioral tests expose mismatches and trigger targeted revisions of motion, geometry, numerics, or material modeling. On evaluated Replica and ScanNet++ scenes, CoDimRecon achieves competitive compositional reconstruction accuracy while additionally producing deformable assets for rod, shell, and solid simulation. We further demonstrate robot interactions across all three representations, including a controlled paper-folding case in which behavioral testing motivates plastic bending. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.36024 — 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 2026-10-07T18:04:24.675Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).