LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Jianhao, Pizzati, Fabio, Pinto, Francesco, Kunze, Lars, Laptev, Ivan, Newman, Paul, Torr, Philip, De Martini, Daniele
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908869721063424
author Yuan, Jianhao
Pizzati, Fabio
Pinto, Francesco
Kunze, Lars
Laptev, Ivan
Newman, Paul
Torr, Philip
De Martini, Daniele
author_facet Yuan, Jianhao
Pizzati, Fabio
Pinto, Francesco
Kunze, Lars
Laptev, Ivan
Newman, Paul
Torr, Philip
De Martini, Daniele
contents Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in disentangling physics correctness from visual appearance in generation. To the end, we introduce LikePhys, a training-free method that evaluates intuitive physics in video diffusion models by distinguishing physically valid and impossible videos using the denoising objective as an ELBO-based likelihood surrogate on a curated dataset of valid-invalid pairs. By testing on our constructed benchmark of twelve scenarios spanning over four physics domains, we show that our evaluation metric, Plausibility Preference Error (PPE), demonstrates strong alignment with human preference, outperforming state-of-the-art evaluator baselines. We then systematically benchmark intuitive physics understanding in current video diffusion models. Our study further analyses how model design and inference settings affect intuitive physics understanding and highlights domain-specific capacity variations across physical laws. Empirical results show that, despite current models struggling with complex and chaotic dynamics, there is a clear trend of improvement in physics understanding as model capacity and inference settings scale.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
Yuan, Jianhao
Pizzati, Fabio
Pinto, Francesco
Kunze, Lars
Laptev, Ivan
Newman, Paul
Torr, Philip
De Martini, Daniele
Computer Vision and Pattern Recognition
Artificial Intelligence
Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in disentangling physics correctness from visual appearance in generation. To the end, we introduce LikePhys, a training-free method that evaluates intuitive physics in video diffusion models by distinguishing physically valid and impossible videos using the denoising objective as an ELBO-based likelihood surrogate on a curated dataset of valid-invalid pairs. By testing on our constructed benchmark of twelve scenarios spanning over four physics domains, we show that our evaluation metric, Plausibility Preference Error (PPE), demonstrates strong alignment with human preference, outperforming state-of-the-art evaluator baselines. We then systematically benchmark intuitive physics understanding in current video diffusion models. Our study further analyses how model design and inference settings affect intuitive physics understanding and highlights domain-specific capacity variations across physical laws. Empirical results show that, despite current models struggling with complex and chaotic dynamics, there is a clear trend of improvement in physics understanding as model capacity and inference settings scale.
title LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.11512