InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion
This work solves the problem of realistic object insertion in videos for video editing applications, representing an incremental improvement over prior methods.
The paper tackles the problem of realistic video object insertion by addressing challenges in 4D scene geometry and handling occlusion and lighting effects, resulting in a framework that significantly outperforms existing models in producing geometrically plausible and visually coherent insertions.
Recent advances in diffusion-based video generation have opened new possibilities for controllable video editing, yet realistic video object insertion (VOI) remains challenging due to limited 4D scene understanding and inadequate handling of occlusion and lighting effects. We present InsertAnywhere, a new VOI framework that achieves geometrically consistent object placement and appearance-faithful video synthesis. Our method begins with a 4D aware mask generation module that reconstructs the scene geometry and propagates user specified object placement across frames while maintaining temporal coherence and occlusion consistency. Building upon this spatial foundation, we extend a diffusion based video generation model to jointly synthesize the inserted object and its surrounding local variations such as illumination and shading. To enable supervised training, we introduce ROSE++, an illumination aware synthetic dataset constructed by transforming the ROSE object removal dataset into triplets of object removed video, object present video, and a VLM generated reference image. Through extensive experiments, we demonstrate that our framework produces geometrically plausible and visually coherent object insertions across diverse real world scenarios, significantly outperforming existing research and commercial models.