Visual Interaction Networks: Learning a Physics Simulator from Video

From just a glance, humans can make rich predictions about the future of a wide range of physical systems. On the other hand, modern approaches from engineering, robotics, and graphics are often restricted to narrow domains or require information about the underlying state. We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations. Our model consists of a perceptual front-end based on convolutional neural networks and a dynamics predictor based on interaction networks. Through joint training, the perceptual front-end learns to parse a dynamic visual scene into a set of factored latent object representations. The dynamics predictor learns to roll these states forward in time by computing their interactions, producing a predicted physical trajectory of arbitrary length. We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems. Our model can also be applied to scenes with invisible objects, inferring their future states from their effects on the visible objects, and can implicitly infer the unknown mass of objects. This work opens new opportunities for model-based decision-making and planning from raw sensory observations in complex physical environments.

[1]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[2]  Terry Winograd,et al.  Procedures As A Representation For Data In A Computer Program For Understanding Natural Language , 1971 .

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Geoffrey E. Hinton,et al.  NeuroAnimator: fast neural network emulation and control of physics-based models , 1998, SIGGRAPH.

[5]  Steven M. Seitz,et al.  Computing the Physical Parameters of Rigid-Body Motion from Video , 2002, ECCV.

[6]  Katherine D. Kinzler,et al.  Core knowledge. , 2007, Developmental science.

[7]  David J. Fleet,et al.  Estimating contact dynamics , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[8]  Joshua B. Tenenbaum,et al.  Noisy Newtons: Unifying process and dependency accounts of causal attribution , 2012, CogSci.

[9]  Jessica B. Hamrick,et al.  Simulation as an engine of physical scene understanding , 2013, Proceedings of the National Academy of Sciences.

[10]  Joshua B. Tenenbaum,et al.  From counterfactual simulation to causal judgment , 2014, CogSci.

[11]  Jiajun Wu,et al.  Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning , 2015, NIPS.

[12]  Barbara Solenthaler,et al.  Data-driven fluid simulations using regression forests , 2015, ACM Trans. Graph..

[13]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Jiajun Wu,et al.  Physics 101: Learning Physical Object Properties from Unlabeled Videos , 2016, BMVC.

[16]  Bernt Schiele,et al.  Long-Term Image Boundary Extrapolation , 2016, ArXiv.

[17]  Jessica B. Hamrick,et al.  Inferring mass in complex scenes by mental simulation , 2016, Cognition.

[18]  Jitendra Malik,et al.  Learning Visual Predictive Models of Physics for Playing Billiards , 2015, ICLR.

[19]  Ali Farhadi,et al.  Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Jitendra Malik,et al.  Learning to Poke by Poking: Experiential Learning of Intuitive Physics , 2016, NIPS.

[21]  Mario Fritz,et al.  To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction , 2016, ArXiv.

[22]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[23]  Rob Fergus,et al.  Learning Physical Intuition of Block Towers by Example , 2016, ICML.

[24]  Ali Farhadi,et al.  "What Happens If..." Learning to Predict the Effect of Forces in Images , 2016, ECCV.

[25]  Stefano Ermon,et al.  Label-Free Supervision of Neural Networks with Physics and Domain Knowledge , 2016, AAAI.

[26]  Niloy J. Mitra,et al.  Learning A Physical Long-term Predictor , 2017, ArXiv.

[27]  Joshua B. Tenenbaum,et al.  A Compositional Object-Based Approach to Learning Physical Dynamics , 2016, ICLR.