Metraipolis › archive › dc_a7bb08351243

DistScene: Object-to-Scene Distillation for 3D Scene Generation — arXiv:2610.06960

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06960
License (as archived)
CC0-1.0
Archived
2026-10-07T13:06:52.454Z
SHA-256 of the archived text
569a4d0df80fbe986172e06942310ea2f346904be8ca2dfd4997dbc81816ee91
Stable URL of this page
https://metraipolis.com/documento/dc_a7bb08351243

How to cite

DistScene: Object-to-Scene Distillation for 3D Scene Generation — arXiv:2610.06960 — arXiv (en), https://arxiv.org/abs/2610.06960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7bb08351243 (Metraipolis archive dc_a7bb08351243, sha256 569a4d0df80fbe986172e06942310ea2f346904be8ca2dfd4997dbc81816ee91)
BibTeX
@misc{dca7bb08351243,
  title = {DistScene: Object-to-Scene Distillation for 3D Scene Generation — arXiv:2610.06960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7bb08351243; sha256 569a4d0df80fbe986172e06942310ea2f346904be8ca2dfd4997dbc81816ee91},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present DistScene, a framework for single-image compositional 3D scene generation by jointly modeling the environment and individual objects. Unlike existing methods that represent scenes primarily as collections of objects, we model the environment as an explicit scene component to provide geometric context for object placement. Specifically, we introduce Scene-Frame Generation, which jointly generates separate environment and object components in a shared coordinate frame, allowing their geometry and relative placement to be learned together. Then we introduce Object-Centric Refinement to refine each object in a local frame with scene context. Finally, we develop Object-to-Scene Distillation to transfer pretrained object-generation priors to scene generation through automatically composed and rendered synthetic scenes. Evaluations on indoor and outdoor benchmarks demonstrate improved scene-level spatial coherence over the evaluated baselines. Project page: this https URL

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/2610.06960 — 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 2026-10-07T12:37:32.831Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).