Metraipolis › archive › dc_7af90f94f423

PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions — arXiv:2610.40453

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40453
License (as archived)
CC0-1.0
Archived
2026-11-01T02:42:25.334Z
SHA-256 of the archived text
14b5f3e71eddeeaebc56c63a82a9c7c8fe53cef15b4a3cb0d87a7feca5062f51
Stable URL of this page
https://metraipolis.com/documento/dc_7af90f94f423

How to cite

PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions — arXiv:2610.40453 — arXiv (en), https://arxiv.org/abs/2610.40453 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7af90f94f423 (Metraipolis archive dc_7af90f94f423, sha256 14b5f3e71eddeeaebc56c63a82a9c7c8fe53cef15b4a3cb0d87a7feca5062f51)
BibTeX
@misc{dc7af90f94f423,
  title = {PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions — arXiv:2610.40453},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40453},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7af90f94f423; sha256 14b5f3e71eddeeaebc56c63a82a9c7c8fe53cef15b4a3cb0d87a7feca5062f51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40453. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present PhysInsert, a framework for physically plausible reference-based object insertion that jointly adapts objects and their surrounding scenes. Existing methods often rely on masked inputs, generation-based pairs, or training pairs with limited viewpoint variation, leaving pose and illumination adaptation and bidirectional object-scene interactions insufficiently constrained. We construct the Insert World dataset with strictly aligned Blender-rendered counterfactual pairs and object references across viewpoints and lighting conditions. Building on these data, Geometry-Guided Adaptation couples a VGGT geometry stream with image and text streams under target-scene feature supervision to guide spatially consistent insertion. Complementary 2D Object-Scene Spatial Supervision jointly supervises object occupancy and environmental changes while grounding spatial instructions in object regions through image-text attention. We introduce PhysInsert-Bench with dedicated cross-environment and cross-view cases requiring illumination and pose adaptation beyond appearance copying. Experiments on PhysInsert-Bench and DreamBooth demonstrate improved image fidelity; a user study further shows more accurate placement and improved lighting integration, perspective, and pose plausibility.

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/2610.40453 — 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 2026-11-01T02:16:43.985Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).