"What Happens If..." Learning to Predict the Effect of Forces in Images

  title={"What Happens If..." Learning to Predict the Effect of Forces in Images},
  author={R. Mottaghi and M. Rastegari and A. Gupta and Ali Farhadi},
  • R. Mottaghi, M. Rastegari, +1 author Ali Farhadi
  • Published 2016
  • Computer Science
  • ArXiv
  • What happens if one pushes a cup sitting on a table toward the edge of the table? How about pushing a desk against a wall? In this paper, we study the problem of understanding the movements of objects as a result of applying external forces to them. For a given force vector applied to a specific location in an image, our goal is to predict long-term sequential movements caused by that force. Doing so entails reasoning about scene geometry, objects, their attributes, and the physical rules that… CONTINUE READING
    85 Citations
    Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
    • 2
    • PDF
    IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
    • 22
    • PDF
    Unsupervised Learning for Physical Interaction through Video Prediction
    • 627
    • PDF
    Learning to Exploit Stability for 3D Scene Parsing
    • 12
    • PDF
    IntPhys: A Benchmark for Visual Intuitive Physics Reasoning
    • 2
    • PDF
    Visual Interaction Networks
    • 80
    • PDF
    Learning and Reasoning with Visual Correspondence in Time
    • Highly Influenced
    • PDF


    Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
    • 112
    • PDF
    Dense Optical Flow Prediction from a Static Image
    • 150
    • PDF
    Show and tell: A neural image caption generator
    • 3,649
    • PDF
    Predicting Object Dynamics in Scenes
    • 78
    • PDF
    Learning to place new objects in a scene
    • 121
    • PDF
    Predictive Visual Models of Physics for Playing Billiards
    • 5
    • Highly Influential
    • PDF
    Action-Conditional Video Prediction using Deep Networks in Atari Games
    • 577
    • PDF
    Microsoft COCO: Common Objects in Context
    • 11,765
    • PDF