PhysInsert:以幾何先驗及雙向物件-場景互動實現物理合理的物件插入
PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions
PhysInsert 是一個參考式物件插入框架,透過共同調整物件及周邊場景,提升插入結果的物理合理性。研究團隊建立 Insert World 數據集,並以幾何引導適配及 2D 物件-場景空間監督,處理物件位置、光照、透視及姿態。實驗顯示,PhysInsert 在 PhysInsert-Bench 和 DreamBooth 上提升圖像保真度,用戶研究亦顯示其物件放置及光照整合更準確。
Published on Oct 29
Authors:
,
,
,
,
,
,
Abstract
PhysInsert enables physically plausible object insertion by jointly adapting objects and scenes using geometry-guided adaptation and spatial supervision on aligned counterfactual data.
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.
View arXiv page View PDF Project page Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.40453 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.40453 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.40453 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co