PhysOmni: 単一画像からの物理基盤マルチオブジェクトシーン生成とリアルタイムインタラクション
PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction
単一画像から物理的に一貫性のある3Dシーンを再構成し、リアルタイムで操作可能なビデオを生成するトレーニング不要のフレームワークを提案。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Xin Zhang, Yabo Chen, Yijie Fang, Wanying Qu, Haibin Huang, Chi Zhang, Feng Xu, Xuelong Li
分類: cs.GR, cs.CV
原文アブストラクト
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D conversion approaches often suffer from object interpenetration. Furthermore, physics-based scene-level 3D generation methods exhibit spatial misalignment, stylized artifacts, and inconsistencies with the input data, restricting their use in realistic interactive video synthesis. We propose PhysOmni, a training-free framework that converts a single image into a physically consistent and controllable video through holistic scene-level 3D reconstruction. By rep?resenting the full scene geometry in a unified spatial coordinate system, PhysOmni resolves object penetration and alignment ambiguity. Unlike prior methods, this formulation enables accurate scene?level multi-object interactions and introduces richer, complex control types for advanced mechanics?based manipulation. By decoupling simulation from rendering, PhysOmni bypasses latency-heavy priors, achieving real-time physical interaction previews paired while preserving photorealistic visual fidelity. Experimental results demonstrate that PhysOmni substantially outperforms prior methods in physical fidelity, spatial coherence, and controllability. Project Page: https://physomni.github.io/
