# Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure

arXiv: https://arxiv.org/abs/1903.01069 · HTML: https://mlsanity.com/paper/1903.01069/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2019.

## Built on by (most cited first, 6 of 6)

- [Defensive Patches for Robust Recognition in the Physical World](https://mlsanity.com/paper/2204.06213/) (2022)
- [IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models](https://mlsanity.com/paper/2501.00848/) (2025)
- [The Art of Deception: Color Visual Illusions and Diffusion Models](https://mlsanity.com/paper/2412.10122/) (2024)
- [Motion Illusions Generated Using Predictive Neural Networks Also Fool Humans](https://mlsanity.com/paper/2112.13243/) (2021)
- [Evaluating Graphical Perception Capabilities of Vision Transformers](https://mlsanity.com/paper/2602.18178/) (2026)
- [Classification, Slippage, Failure and Discovery](https://mlsanity.com/paper/2104.03886/) (2021)

## Abstract (arXiv)

The Gestalt laws of perceptual organization, which describe how visual elements in an image are grouped and interpreted, have traditionally been thought of as innate despite their ecological validity. We use deep-learning methods to investigate whether natural scene statistics might be sufficient to derive the Gestalt laws. We examine the law of closure, which asserts that human visual perception tends to "close the gap" by assembling elements that can jointly be interpreted as a complete figure or object. We demonstrate that a state-of-the-art convolutional neural network, trained to classify natural images, exhibits closure on synthetic displays of edge fragments, as assessed by similarity of internal representations. This finding provides support for the hypothesis that the human perceptual system is even more elegant than the Gestaltists imagined: a single law---adaptation to the statistical structure of the environment---might suffice as fundamental.