Pith. sign in

REVIEW 2 cited by

Visual Interaction Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1706.01433 v1 pith:PNJCKE4K submitted 2017-06-05 cs.CV

classification cs.CV
keywords dynamicsphysicalvisualinteractionfuturemodelnetworksobjects
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

From just a glance, humans can make rich predictions about the future state of a wide range of physical systems. On the other hand, modern approaches from engineering, robotics, and graphics are often restricted to narrow domains and require direct measurements of the underlying states. 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 and dynamics, 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. Our results demonstrate that the perceptual module and the object-based dynamics predictor module can induce factored latent representations that support accurate dynamical predictions. This work opens new opportunities for model-based decision-making and planning from raw sensory observations in complex physical environments.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments

    cs.CV 2025-06 conditional novelty 6.0 of 10

    IntPhys 2 evaluates models on permanence, immutability, continuity, and solidity in synthetic videos, and finds most models near chance while humans near perfect.

  2. Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System

    physics.ao-ph 2025-05 conditional novelty 5.0 of 10

    An adapted GraphCast graph neural network trained on satellite sea surface temperature outperforms ConvLSTM and the GLORYS reanalysis for medium-range forecasts in the Canary Current upwelling system.

Pith tools