EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Gestalt Vision: Evaluating Perceptual Grouping in Neural Visual Reasoning

Jingyuan Sha, Kristian Kersting, Devendra Singh Dhami

Neurosymbolic Artificial Intelligence · 2026-07 · 2

DOI: 10.1177/29498732261469488 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurosymbolic Artificial Intelligence, online erschienen am 29.07.2026. Verfasst von Jingyuan Sha und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gestalt principles, established in the 1920s, describe how humans perceive individual elements as cohesive wholes. These principles, including proximity, similarity, closure, continuity, symmetry, and so on, play a fundamental role in human perception, enabling structured visual interpretation. Despite their significance, existing Artificial Intelligence (AI) benchmarks fail to assess models’ ability to infer patterns at the group level, where multiple objects following the same Gestalt principle are considered as a group using these principles. To address this gap, we introduce Gestalt Vision, a framework designed to evaluate AI models’ ability to not only identify groups within patterns but also reason about the underlying logical rules governing these patterns. Gestalt Vision provides structured visual tasks and baseline evaluations spanning neural and neural-symbolic approaches, uncovering key limitations in current models’ ability to perform human-like visual cognition. Our findings emphasize the necessity of incorporating richer perceptual mechanisms into AI reasoning frameworks. By bridging the gap between human perception and computational models, Gestalt Vision offers a crucial step toward developing AI systems with improved perceptual organization and visual reasoning capabilities.

Zitieren

APA

Sha, J., Kersting, K., & Dhami, D. S. (2026). Gestalt Vision: Evaluating Perceptual Grouping in Neural Visual Reasoning. Neurosymbolic Artificial Intelligence, 2. https://doi.org/10.1177/29498732261469488

Vancouver

Sha J, Kersting K, Dhami DS. Gestalt Vision: Evaluating Perceptual Grouping in Neural Visual Reasoning. Neurosymbolic Artificial Intelligence. 2026;2. doi:10.1177/29498732261469488

BibTeX
@article{Sha2026,
  author = {Sha, Jingyuan and Kersting, Kristian and Dhami, Devendra Singh},
  title = {Gestalt Vision: Evaluating Perceptual Grouping in Neural Visual Reasoning},
  journal = {Neurosymbolic Artificial Intelligence},
  year = {2026},
  volume = {2},
  doi = {10.1177/29498732261469488}
}
Kostenlos starten →