IMPACT: Image-Conditioned Motion with Physics-Aware Collision and Trajectory Guidance for Video Generation
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Project page: https://weiweiwiewei.github.io/impact
License: http://creativecommons.org/licenses/by/4.0/
The gist: Visually realistic video generation does not guarantee physically consistent motion.
Terminology
Abstract
Visually realistic video generation does not guarantee physically consistent motion. Generated objects may exhibit implausible collision responses or rebounds without energy dissipation, while even physically valid motion predictions may not be faithfully realized during synthesis. We propose IMPACT, a physics-state-driven image-to-video framework that addresses these challenges by coupling explicit dynamics prediction with complementary sparse--dense physical guidance. A learnably calibrated Physics State Generator unifies continuous free-flight dynamics with discrete collision responses, linking impact timing, post-impact velocity, rebound attenuation, and eventual settling within a coherent physical-state sequence. To translate this evolution into effective generative constraints, IMPACT derives sparse trajectories and dense region-level motion priors from the same physical rollout. Sparse trajectories constrain global object displacement, while dense priors guide diffusion sampling to encourage coherent object-region motion and suppress unwanted background changes. Their shared physical basis coordinates global and local motion guidance to reduce prediction--generation mismatch. Experiments on 100 controlled sphere--plane collision scenes spanning different material combinations and visual environments demonstrate improved physical plausibility over representative general-purpose, physics-grounded, and motion-controllable baselines. The project repository is available at https://weiweiwiewei.github.io/impact
Sources
- Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model
- PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
- Think Before You Diffuse: Infusing Physical Rules into Video Diffusion
- NEWTON: Agentic Planning for Physically Grounded Video Generation
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- LTX-Video: Realtime Video Latent Diffusion
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs