# Interpretable Intuitive Physics Model

arXiv: https://arxiv.org/abs/1808.10002 · HTML: https://mlsanity.com/paper/1808.10002/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2018.

## Built on by (most cited first, 19 of 19)

- [Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications](https://mlsanity.com/paper/2211.08064/) (2022)
- [Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning](https://mlsanity.com/paper/2103.16564/) (2021)
- [When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning](https://mlsanity.com/paper/2203.16797/) (2022)
- [Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language](https://mlsanity.com/paper/2110.15358/) (2021)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [Doubly Right Object Recognition: A Why Prompt for Visual Rationales](https://mlsanity.com/paper/2212.06202/) (2022)
- [Towards a Collective Agenda on AI for Earth Science Data Analysis](https://mlsanity.com/paper/2104.05107/) (2021)
- [PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos](https://mlsanity.com/paper/2412.01800/) (2024)
- [A Survey on Machine Learning Approaches for Modelling Intuitive Physics](https://mlsanity.com/paper/2202.06481/) (2022)
- [PIP: Physical Interaction Prediction via Mental Simulation with Span Selection](https://mlsanity.com/paper/2109.04683/) (2021)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [Pretraining on Interactions for Learning Grounded Affordance Representations](https://mlsanity.com/paper/2207.02272/) (2022)
- [Compositional Law Parsing with Latent Random Functions](https://mlsanity.com/paper/2209.09115/) (2022)
- [Distilling Governing Laws and Source Input for Dynamical Systems from Videos](https://mlsanity.com/paper/2205.01314/) (2022)
- [Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel](https://mlsanity.com/paper/2505.22861/) (2025)
- [Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos](https://mlsanity.com/paper/2106.04776/) (2021)
- [T3VIP: Transformation-based 3D Video Prediction](https://mlsanity.com/paper/2209.11693/) (2022)
- [Emergent Compositional Communication for Latent World Properties](https://mlsanity.com/paper/2604.03266/) (2026)
- [Understanding in Artificial Intelligence](https://mlsanity.com/paper/2101.06573/) (2021)

## Abstract (arXiv)

Humans have a remarkable ability to use physical commonsense and predict the effect of collisions. But do they understand the underlying factors? Can they predict if the underlying factors have changed? Interestingly, in most cases humans can predict the effects of similar collisions with different conditions such as changes in mass, friction, etc. It is postulated this is primarily because we learn to model physics with meaningful latent variables. This does not imply we can estimate the precise values of these meaningful variables (estimate exact values of mass or friction). Inspired by this observation, we propose an interpretable intuitive physics model where specific dimensions in the bottleneck layers correspond to different physical properties. In order to demonstrate that our system models these underlying physical properties, we train our model on collisions of different shapes (cube, cone, cylinder, spheres etc.) and test on collisions of unseen combinations of shapes. Furthermore, we demonstrate our model generalizes well even when similar scenes are simulated with different underlying properties.