Metraipolis › archive › dc_2bd4f20ee5de
Scene Retargeting: Learning Object Placement with Analogical Transfer — arXiv:2609.36801
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36801
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:27.663Z
- SHA-256 of the archived text
dfc7d080866b033300c93430ec218c2cdfaedb6f6379f21472bf66465b74e10d- Stable URL of this page
https://metraipolis.com/documento/dc_2bd4f20ee5de
How to cite
Scene Retargeting: Learning Object Placement with Analogical Transfer — arXiv:2609.36801 — arXiv (en), https://arxiv.org/abs/2609.36801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bd4f20ee5de (Metraipolis archive dc_2bd4f20ee5de, sha256 dfc7d080866b033300c93430ec218c2cdfaedb6f6379f21472bf66465b74e10d)
BibTeX
@misc{dc2bd4f20ee5de,
title = {Scene Retargeting: Learning Object Placement with Analogical Transfer — arXiv:2609.36801},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36801},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bd4f20ee5de; sha256 dfc7d080866b033300c93430ec218c2cdfaedb6f6379f21472bf66465b74e10d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Interactive simulations of embodied AI or spatial computing applications build on realistic 3D scenes that support daily activities. However, sparse, irregular layout structures impose scene-specific physical constraints, making it hard to define a generalizable framework for generating similar functional context. We formalize Scene Retargeting as stably transferring the semantically coherent spatial organization across layouts, rather than relying on textual descriptions or pairwise relationships. Our cluster-wise transfer flexibly handles mismatched object instances and adapts to distinctive floor plans. We optimize to preserve the rich semantic context of individual clusters by respecting the spatial distribution of foundation features. We can then impose physical constraints to refine wall contacts, pairwise alignment, or clear passageways and openings. Our framework outperforms state-of-the-art methods on layout generation on the 3D-FRONT dataset, and demonstrates downstream applications including real-to-sim transfer, analogical trajectory transfer, and multi-reference composition. 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). Pagina del lavoro: https://arxiv.org/abs/2609.36801 — 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 2026-10-07T18:04:24.746Z 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).