AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Interpretable Intuitive Physics Model

Tian Ye, Xiaolong Wang, James Davidson, Abhinav Gupta

ECCV 2018 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning · 57 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add disentanglement constraints on bottleneck (interpretable model) vs end-to-end baseline (ablation)Intuitive physics model · Unseen shape combinationspixel prediction error: 95.6 -> 87.3Improved
add disentanglement constraints on bottleneck vs baseline (ablation)Intuitive physics model · Interpolation shape 5pixel prediction error: 173.80 -> 138.04Improved
add disentanglement constraints on bottleneck vs baseline (ablation)Intuitive physics model · Interpolation parameter 3pixel prediction error: 299.88 -> 154.09Improved
add disentanglement constraints on bottleneck vs baseline (ablation)Intuitive physics model · Ratio parameter ratio 3pixel prediction error: 490.92 -> 157.10Improved
add disentanglement constraints on bottleneck vs baseline (ablation)Intuitive physics model · Ratio shape ratio 2pixel prediction error: 345.60 -> 110.79Improved
predict from ground-truth physics parameters and optical flows (Flow + Physics) instead of learned interpretable latent (ablation)Prediction model · Interpolation parameter 3pixel prediction error: 154.09 -> 671.51Hurt
predict via supervised optical flow of frames 4-5 instead of pixels of 5th frame (ablation)Prediction model · Unseen shape combinationspixel error: 87.3 -> 118.8Hurt
use linear model on optical flows instead of the learned model (ablation)Prediction model · Unseen shape combinationspixel error: 87.3 -> 292.5Hurt
use staggered training (curriculum over properties) (ablation)Intuitive physics model · Trainingnot reportedImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy