Seeing the Wind from a Falling Leaf
By: Zhiyuan Gao , Jiageng Mao , Hong-Xing Yu and more
Potential Business Impact:
Shows invisible forces like wind from videos.
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}.
Similar Papers
Learning an Implicit Physics Model for Image-based Fluid Simulation
CV and Pattern Recognition
Makes videos of liquids move like real physics.
Iterative Motion Compensation for Canonical 3D Reconstruction from UAV Plant Images Captured in Windy Conditions
CV and Pattern Recognition
Creates clear 3D pictures of plants, even when windy.
CORONA-Fields: Leveraging Foundation Models for Classification of Solar Wind Phenomena
CV and Pattern Recognition
Helps predict dangerous space storms better.