Metraipolis › archive › dc_2ae38ccf302e

A Bridge from Paste to Place: Physics-Guided One-Step Image Composition via Object-Scene Interaction — arXiv:2611.09387

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09387
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:19.542Z
SHA-256 of the archived text
83606e31920b1e9eb180517ac8a8b131d358249655eeee971e5d8feece7f26d3
Stable URL of this page
https://metraipolis.com/documento/dc_2ae38ccf302e

How to cite

A Bridge from Paste to Place: Physics-Guided One-Step Image Composition via Object-Scene Interaction — arXiv:2611.09387 — arXiv (en), https://arxiv.org/abs/2611.09387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ae38ccf302e (Metraipolis archive dc_2ae38ccf302e, sha256 83606e31920b1e9eb180517ac8a8b131d358249655eeee971e5d8feece7f26d3)
BibTeX
@misc{dc2ae38ccf302e,
  title = {A Bridge from Paste to Place: Physics-Guided One-Step Image Composition via Object-Scene Interaction — arXiv:2611.09387},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09387},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ae38ccf302e; sha256 83606e31920b1e9eb180517ac8a8b131d358249655eeee971e5d8feece7f26d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Realistic image composition must make a pasted object appear naturally present in a scene while preserving the fine details of both foreground and background. Reference-based insertion methods can change object pose and appearance, while foreground harmonization methods and shadow-specific synthesis methods each address only part of this task. An efficient, unified solution to this task remains an open challenge. We introduce Paste2Place, an end-to-end, physics-guided flow-based model that learns a direct, one-step latent bridge from pasted inputs to realistic composites, guided by explicit albedo-shading-residual decomposition and recomposition within the model. To support model training and evaluation, we develop a Blender rendering and validation pipeline to generate paired composites with physical annotations, and construct real-scene pairs from open-source object-removal data. This effort yields 86,273 training pairs and a 1,500-example benchmark. Extensive qualitative and quantitative experiments demonstrate that Paste2Place achieves substantial advantages in image composition quality and inference speed. Overall, our work provides a clear task definition and an effective solution for image composition, and fills a gap in large-scale, high-quality datasets and benchmarks for training and evaluating image composition.

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/2611.09387 — 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 2026-11-09T22:37:47.227Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).