Saved in:
Bibliographic Details
Main Authors: Yang, Xindi, Li, Baolu, Zhang, Yiming, Yin, Zhenfei, Bai, Lei, Ma, Liqian, Wang, Zhiyong, Cai, Jianfei, Wong, Tien-Tsin, Lu, Huchuan, Jia, Xu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.23368
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916673839169536
author Yang, Xindi
Li, Baolu
Zhang, Yiming
Yin, Zhenfei
Bai, Lei
Ma, Liqian
Wang, Zhiyong
Cai, Jianfei
Wong, Tien-Tsin
Lu, Huchuan
Jia, Xu
author_facet Yang, Xindi
Li, Baolu
Zhang, Yiming
Yin, Zhenfei
Bai, Lei
Ma, Liqian
Wang, Zhiyong
Cai, Jianfei
Wong, Tien-Tsin
Lu, Huchuan
Jia, Xu
contents Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics, resulting in incorrect dynamics and event sequences. To address this limitation, we propose a novel two-stage image-to-video generation framework that explicitly incorporates physics with vision and language informed physical prior. In the first stage, we employ a Vision Language Model (VLM) as a coarse-grained motion planner, integrating chain-of-thought and physics-aware reasoning to predict a rough motion trajectories/changes that approximate real-world physical dynamics while ensuring the inter-frame consistency. In the second stage, we use the predicted motion trajectories/changes to guide the video generation of a VDM. As the predicted motion trajectories/changes are rough, noise is added during inference to provide freedom to the VDM in generating motion with more fine details. Extensive experimental results demonstrate that our framework can produce physically plausible motion, and comparative evaluations highlight the notable superiority of our approach over existing methods. More video results are available on our Project Page: https://madaoer.github.io/projects/physically_plausible_video_generation.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23368
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior
Yang, Xindi
Li, Baolu
Zhang, Yiming
Yin, Zhenfei
Bai, Lei
Ma, Liqian
Wang, Zhiyong
Cai, Jianfei
Wong, Tien-Tsin
Lu, Huchuan
Jia, Xu
Computer Vision and Pattern Recognition
Artificial Intelligence
Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics, resulting in incorrect dynamics and event sequences. To address this limitation, we propose a novel two-stage image-to-video generation framework that explicitly incorporates physics with vision and language informed physical prior. In the first stage, we employ a Vision Language Model (VLM) as a coarse-grained motion planner, integrating chain-of-thought and physics-aware reasoning to predict a rough motion trajectories/changes that approximate real-world physical dynamics while ensuring the inter-frame consistency. In the second stage, we use the predicted motion trajectories/changes to guide the video generation of a VDM. As the predicted motion trajectories/changes are rough, noise is added during inference to provide freedom to the VDM in generating motion with more fine details. Extensive experimental results demonstrate that our framework can produce physically plausible motion, and comparative evaluations highlight the notable superiority of our approach over existing methods. More video results are available on our Project Page: https://madaoer.github.io/projects/physically_plausible_video_generation.
title VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.23368