Seeing the Wind from a Falling Leaf

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Zhiyuan, Mao, Jiageng, Yu, Hong-Xing, Lou, Haozhe, Jia, Emily Yue-Ting, Barbic, Jernej, Wu, Jiajun, Wang, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917114421444608
author Gao, Zhiyuan
Mao, Jiageng
Yu, Hong-Xing
Lou, Haozhe
Jia, Emily Yue-Ting
Barbic, Jernej
Wu, Jiajun
Wang, Yue
author_facet Gao, Zhiyuan
Mao, Jiageng
Yu, Hong-Xing
Lou, Haozhe
Jia, Emily Yue-Ting
Barbic, Jernej
Wu, Jiajun
Wang, Yue
contents A longstanding goal in computer vision is to model motions from videos, while the representations behind motions, i.e. the invisible physical interactions that cause objects to deform and move, remain largely unexplored. In this paper, we study how to recover the invisible forces from visual observations, e.g., estimating the wind field by observing a leaf falling to the ground. Our key innovation is an end-to-end differentiable inverse graphics framework, which jointly models object geometry, physical properties, and interactions directly from videos. Through backpropagation, our approach enables the recovery of force representations from object motions. We validate our method on both synthetic and real-world scenarios, and the results demonstrate its ability to infer plausible force fields from videos. Furthermore, we show the potential applications of our approach, including physics-based video generation and editing. We hope our approach sheds light on understanding and modeling the physical process behind pixels, bridging the gap between vision and physics. Please check more video results in our \href{https://chaoren2357.github.io/seeingthewind/}{project page}.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing the Wind from a Falling Leaf
Gao, Zhiyuan
Mao, Jiageng
Yu, Hong-Xing
Lou, Haozhe
Jia, Emily Yue-Ting
Barbic, Jernej
Wu, Jiajun
Wang, Yue
Computer Vision and Pattern Recognition
A longstanding goal in computer vision is to model motions from videos, while the representations behind motions, i.e. the invisible physical interactions that cause objects to deform and move, remain largely unexplored. In this paper, we study how to recover the invisible forces from visual observations, e.g., estimating the wind field by observing a leaf falling to the ground. Our key innovation is an end-to-end differentiable inverse graphics framework, which jointly models object geometry, physical properties, and interactions directly from videos. Through backpropagation, our approach enables the recovery of force representations from object motions. We validate our method on both synthetic and real-world scenarios, and the results demonstrate its ability to infer plausible force fields from videos. Furthermore, we show the potential applications of our approach, including physics-based video generation and editing. We hope our approach sheds light on understanding and modeling the physical process behind pixels, bridging the gap between vision and physics. Please check more video results in our \href{https://chaoren2357.github.io/seeingthewind/}{project page}.
title Seeing the Wind from a Falling Leaf
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00762