AI Paper Atlas

Research map / 3D vision / 3D generation

Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations

Kevin Smith, Lingjie Mei, Shunyu Yao, Jiajun Wu, Elizabeth Spelke, Josh Tenenbaum, Tomer Ullman

NeurIPS 2019 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 58 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
use coarse object-centric perception, stochastic physics and particle filtering instead of pixel-prediction networkspixel-based baselines (GAN best) · VoE test set averagerelative accuracy: 0.63 -> 0.79Improved
use ADEPT instead of GANADEPT · VoE Overturn (long)relative accuracy: 0.84 -> 0.73Hurt
use ADEPT instead of GANADEPT · VoE Blockrelative accuracy: 0.44 -> 0.68Improved
use ADEPT instead of GANADEPT · IntPhys O1relative accuracy: 0.53 -> 0.73Improved
use approximate object representation for novel object categoriesADEPT · VoE Unseen categoriesrelative accuracy: 0.61 -> 0.68Improved
use ADEPT instead of Encoder-decoder for human-like surpriseADEPT · Human-model deviationRMSE: 1.10 -> 0.40Improved

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