EUVIMEDEUVIMED entdecken
Crossref

From pixels to physics: an image-computable model of physical predictions

Cognitive Science Society 2025, Nishad Gothoskar, Kevin A. Smith, Joshua B. Tenenbaum, Haoliang Wang

eScholarship (California Digital Library) · 18.06.2025

DOI: 10.48448/gfe1-hn84 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eScholarship (California Digital Library), erschienen am 18.06.2025. Verfasst von Cognitive Science Society 2025 und 4 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Having reasonable expectations of how scenes will unfold is crucial in our life. One prominent hypothesis is that we perform probabilistic physics simulation in our mind. However, the question of how people infer underlying scenes from observations and how this affects downstream predictions about physics interactions is under explored. Current models usually make simplified assumptions that the 3D geometric states of objects are already given. To better understand the role of perceptual uncertainty in people’s physical predictions, we explore the idea of vision as inverse graphics and design a model that can infer a posterior distribution of object states given the raw visual inputs. This perceptual uncertainty is then propagated to a probabilistic physics simulation model to derive physical predictions. We compared the model’s predictions and generalizations on a wide range of physical scenarios from the Physion dataset and found that it captured both participants’ successes and error patterns.

Schlagwörter

physical predictionsperceptual uncertaintyinverse graphicserror propagation

Zitieren

APA

2025, C. S. S., Gothoskar, N., Smith, K. A., Tenenbaum, J. B., & Wang, H. (2025). From pixels to physics: an image-computable model of physical predictions. eScholarship (California Digital Library). https://doi.org/10.48448/gfe1-hn84

Vancouver

2025 CSS, Gothoskar N, Smith KA, Tenenbaum JB, Wang H. From pixels to physics: an image-computable model of physical predictions. eScholarship (California Digital Library). 2025. doi:10.48448/gfe1-hn84

BibTeX
@article{2025,
  author = {2025, Cognitive Science Society and Gothoskar, Nishad and Smith, Kevin A. and Tenenbaum, Joshua B. and Wang, Haoliang},
  title = {From pixels to physics: an image-computable model of physical predictions},
  journal = {eScholarship (California Digital Library)},
  year = {2025},
  doi = {10.48448/gfe1-hn84}
}
Kostenlos starten →