PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding

TL;DR

PhysChoreo is a new framework that generates physically realistic and controllable videos from a single image by estimating physical properties and simulating dynamic behaviors over time.

Contribution

It introduces a two-stage process combining part-aware physical property estimation and physically editable simulation for improved video realism and controllability.

Findings

Outperforms state-of-the-art methods on multiple metrics.

Generates videos with diverse dynamic behaviors.

Ensures physical plausibility in generated videos.

Abstract

While recent video generation models have achieved significant visual fidelity, they often suffer from the lack of explicit physical controllability and plausibility. To address this, some recent studies attempted to guide the video generation with physics-based rendering. However, these methods face inherent challenges in accurately modeling complex physical properties and effectively control ling the resulting physical behavior over extended temporal sequences. In this work, we introduce PhysChoreo, a novel framework that can generate videos with diverse controllability and physical realism from a single image. Our method consists of two stages: first, it estimates the static initial physical properties of all objects in the image through part-aware physical property reconstruction. Then, through temporally instructed and physically editable simulation, it synthesizes high-quality videos with rich dynamic behaviors and physical realism. Experimental results show that PhysChoreo can generate videos with rich behaviors and physical realism, outperforming state-of-the-art methods on multiple evaluation metrics.