Individuation of 3D perceptual units from neurogeometry of binocular cells

We model the functional architecture of the early stages of three-dimensional vision by extending the neurogeometric sub-Riemannian model for stereo-vision introduced in BCSZ23. A new framework for correspondence is introduced that integrates a neural-based algorithm to achieve stereo correspondence...

Full description

Saved in:

Bibliographic Details
Main Authors	Bolelli, Maria Virginia, Citti, Giovanna, Sarti, Alessandro, Zucker, Steven W
Format	Journal Article
Language	English
Published	03.10.2024
Subjects	Computer Science - Computer Vision and Pattern Recognition Mathematics - Differential Geometry Quantitative Biology - Neurons and Cognition
Online Access	Get full text
DOI	10.48550/arxiv.2410.02870

Cover

More Information
Summary:	We model the functional architecture of the early stages of three-dimensional vision by extending the neurogeometric sub-Riemannian model for stereo-vision introduced in BCSZ23. A new framework for correspondence is introduced that integrates a neural-based algorithm to achieve stereo correspondence locally while, simultaneously, organizing the corresponding points into global perceptual units. The result is an effective scene segmentation. We achieve this using harmonic analysis on the sub-Riemannian structure and show, in a comparison against Riemannian distance, that the sub-Riemannian metric is central to the solution.
DOI:	10.48550/arxiv.2410.02870