VOID: Video Object and Interaction Deletion
This addresses the challenge of physically plausible video editing for applications like film production or augmented reality, though it is incremental as it builds on existing video object removal and diffusion model techniques.
The paper tackles the problem of video object removal when the removed object has significant physical interactions like collisions, where existing methods fail to produce plausible results. The proposed VOID framework uses a vision-language model to identify affected regions and a video diffusion model to generate physically consistent outcomes, showing better preservation of scene dynamics compared to prior methods.
Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections. However, when the removed object has more significant interactions, such as collisions with other objects, current models fail to correct them and produce implausible results. We present VOID, a video object removal framework designed to perform physically-plausible inpainting in these complex scenarios. To train the model, we generate a new paired dataset of counterfactual object removals using Kubric and HUMOTO, where removing an object requires altering downstream physical interactions. During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods. We hope this framework sheds light on how to make video editing models better simulators of the world through high-level causal reasoning.