Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning

  title={Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning},
  author={Jiajun Wu and Ilker Yildirim and Joseph J. Lim and Bill Freeman and Joshua B. Tenenbaum},
Humans demonstrate remarkable abilities to predict physical events in dynamic scenes, and to infer the physical properties of objects from static images. We propose a generative model for solving these problems of physical scene understanding from real-world videos and images. At the core of our generative model is a 3D physics engine, operating on an object-based representation of physical properties, including mass, position, 3D shape, and friction. We can infer these latent properties using… CONTINUE READING
Highly Cited
This paper has 159 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 99 extracted citations

Computer Vision – ECCV 2016

Lecture Notes in Computer Science • 2016
View 10 Excerpts
Highly Influenced

Deep reinforcement learning

View 4 Excerpts
Highly Influenced

Interactive Perception: Leveraging Action in Perception and Perception in Action

IEEE Transactions on Robotics • 2017
View 5 Excerpts
Highly Influenced

Towards intuitive rigid-body physics through parameter search

2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids) • 2017
View 3 Excerpts
Highly Influenced

Situated Mappings : Augmented-Reality Clay and Adaptive Interfacing

Julia Litman-Cleper, Takehiko Nagakura
View 2 Excerpts
Highly Influenced

3D Interpreter Networks for Viewer-Centered Wireframe Modeling

International Journal of Computer Vision • 2018
View 2 Excerpts

160 Citations

Citations per Year
Semantic Scholar estimates that this publication has 160 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 13 references

3D Reasoning from Blocks to Stability

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015
View 1 Excerpt

Detecting potential falling objects by inferring human action and natural disturbance

2014 IEEE International Conference on Robotics and Automation (ICRA) • 2014
View 1 Excerpt

Simulation as an engine of physical scene understanding.

Proceedings of the National Academy of Sciences of the United States of America • 2013
View 2 Excerpts

Tracking deformable objects with point clouds

2013 IEEE International Conference on Robotics and Automation • 2013

Bullet physics engine

Erwin Coumans
Open Source Software: http://bulletphysics. org, • 2010
View 2 Excerpts

The origin of concepts

Susan Carey
View 1 Excerpt

Similar Papers

Loading similar papers…