Metraipolis › archive › dc_eec1e47a5cc2

CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image — arXiv:2609.25654

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25654
License (as archived)
CC0-1.0
Archived
2026-10-08T15:08:23.895Z
SHA-256 of the archived text
9478859fa79db41a0d7d8a2297ce08e03c00da7b564d2e0e3fa6b80fb1e5f15c
Stable URL of this page
https://metraipolis.com/documento/dc_eec1e47a5cc2

How to cite

CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image — arXiv:2609.25654 — arXiv (en), https://arxiv.org/abs/2609.25654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eec1e47a5cc2 (Metraipolis archive dc_eec1e47a5cc2, sha256 9478859fa79db41a0d7d8a2297ce08e03c00da7b564d2e0e3fa6b80fb1e5f15c)
BibTeX
@misc{dceec1e47a5cc2,
  title = {CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image — arXiv:2609.25654},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25654},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eec1e47a5cc2; sha256 9478859fa79db41a0d7d8a2297ce08e03c00da7b564d2e0e3fa6b80fb1e5f15c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robots operating safely in cluttered everyday environments often need to infer scene geometry from partial observations. Methods that detect objects in 2D and reconstruct them independently struggle in such scenes: a missed object is never reconstructed, a merged detection can fuse two objects, and separately reconstructed meshes may overlap or fail to touch their supporting surfaces. We introduce CODA (Complete Once, Decompose Afterward), a generative model that instead reconstructs the complete scene geometry from a single unsegmented RGB-D image, then separates the surface into the surrounding environment and movable objects. Still, generated scene geometry can drift from the observed partial point cloud. To reduce this drift, CODA uses two explicit 3D grounding mechanisms to keep reconstructed geometry consistent with observed surfaces while completing unseen regions. Experiments on HomebrewedDB and our custom cluttered-scene dataset show more accurate reconstructions and a higher fraction of objects remaining in place under simulated gravity than both object-first and scene-first baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25654 — 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 2026-10-08T14:37:29.543Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).