titlePhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions
authorsYue Gong, Le Zhang, Rui Chen, Song Chang, Xiaochao Qu, Luoqi Liu, Ting Liu, Yebin Liu
date2026-10-29
venuearXiv (preprint, not peer reviewed)
idarXiv:2610.40453
upvotes8 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf
abstractWe 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.

cite

@misc{gong2026physinsert,
  title={PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions},
  author={Yue Gong and Le Zhang and Rui Chen and Song Chang and Xiaochao Qu and Luoqi Liu and Ting Liu and Yebin Liu},
  year={2026},
  eprint={2610.40453},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2610.40453}
}