Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images

• URL: http://arxiv.org/abs/2607.08932v1
• Date: Thu, 09 Jul 2026 21:00:46 GMT
• Title: Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
• Abstract summary: We evaluate shape-based figure-ground organization in Vision Transformers (ViTs)<n>ViTs encode surroundedness and convexity, and that probes trained on natural images generalize zero-shot to artificial stimuli.<n>For symmetry we observe mixed results: the cue is encoded for uniformly colored but not for textured regions.
• Score: 4.927738810841049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Figure-ground organization in the human visual system relies on several shape-based cues, including surroundedness, convexity, and symmetry. While these cues have been extensively studied using abstract stimuli, little is known about how they operate under natural conditions or how they arise from the statistics of natural scenes. Deep neural networks offer a promising path forward: a model that relies on the same figure-ground cues as humans would provide tractable experimental access to the underlying mechanisms. In this study, we evaluate shape-based figure-ground organization in Vision Transformers (ViTs), for which prior work has demonstrated the emergence of object-based grouping. We test 25 ViTs spanning supervised and self-supervised training objectives, by fitting linear probes to predict figure-ground assignment from intermediate patch representations using both natural images and controlled artificial stimuli that isolate individual cues. Our results show that ViTs robustly encode surroundedness and convexity, and that probes trained on natural images generalize zero-shot to artificial stimuli across several models. For symmetry we observe mixed results: the cue is encoded for uniformly colored but not for textured regions. Taken together, our findings demonstrate that Gestalt-like figure-ground cues can be learned from natural scene statistics and position ViTs as a compelling model system for studying the computational mechanisms of perceptual organization. Code and data is available at https://github.com/mtangemann/mlvbench

Related papers

• Human-level 3D shape perception emerges from multi-view learning [63.048728487674815]
  We develop a modeling framework that predicts human 3D shape inferences for arbitrary objects.<n>We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data.<n>We find that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data.
  arXiv  Detail & Related papers  (2026-02-19T18:56:05Z)
• A neuromorphic model of the insect visual system for natural image processing [0.8602553195689513]
  Insect vision supports complex behaviors including associative learning, navigation, and object detection.<n>Here, we introduce a bio-inspired vision model that transforms dense visual input into sparse, discriminative codes.<n>We evaluate the resulting representations on flower recognition tasks and natural image benchmarks.
  arXiv  Detail & Related papers  (2026-02-06T05:54:28Z)
• Synthesis and Perceptual Scaling of High Resolution Naturalistic Images Using Stable Diffusion [0.43748379918040853]
  We create a stimulus set of photorealistic images characterized by gradual transitions.<n>For each object scene, we generate 10 variants that are ordered along a perceptual continuum.<n>This ordering is also predictive of confusability of stimuli in a working memory experiment.
  arXiv  Detail & Related papers  (2024-10-16T20:49:19Z)
• Neural Rendering of Humans in Novel View and Pose from Monocular Video [68.37767099240236]
  We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.
  arXiv  Detail & Related papers  (2022-04-04T03:09:20Z)
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies [78.17425779503047]
  We propose a novel neural implicit representation for the human body. It is fully differentiable and optimizable with disentangled shape and pose latent spaces. Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
  arXiv  Detail & Related papers  (2021-11-30T04:10:57Z)
• Scene Synthesis via Uncertainty-Driven Attribute Synchronization [52.31834816911887]
  This paper introduces a novel neural scene synthesis approach that can capture diverse feature patterns of 3D scenes. Our method combines the strength of both neural network-based and conventional scene synthesis approaches.
  arXiv  Detail & Related papers  (2021-08-30T19:45:07Z)
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control [80.79820002330457]
  We propose a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses. Our method achieves better quality than the state-of-the-arts on playback as well as novel pose synthesis, and can even generalize well to new poses that starkly differ from the training poses.
  arXiv  Detail & Related papers  (2021-06-03T17:40:48Z)
• Intriguing Properties of Vision Transformers [114.28522466830374]
  Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. We systematically study this question via an extensive set of experiments and comparisons with a high-performing convolutional neural network (CNN) We show effective features of ViTs are due to flexible receptive and dynamic fields possible via the self-attention mechanism.
  arXiv  Detail & Related papers  (2021-05-21T17:59:18Z)
• Appearance Consensus Driven Self-Supervised Human Mesh Recovery [67.20942777949793]
  We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images. We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks. The resulting colored mesh prediction opens up the usage of our framework for a variety of appearance-related tasks beyond the pose and shape estimation.
  arXiv  Detail & Related papers  (2020-08-04T05:40:39Z)
• Seeing eye-to-eye? A comparison of object recognition performance in humans and deep convolutional neural networks under image manipulation [0.0]
  This study aims towards a behavioral comparison of visual core object recognition performance between humans and feedforward neural networks. Analyses of accuracy revealed that humans not only outperform DCNNs on all conditions, but also display significantly greater robustness towards shape and most notably color alterations.
  arXiv  Detail & Related papers  (2020-07-13T10:26:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.