The Role of Cyclopean-Eye in Stereo Vision
Abstract
This work investigates the geometric foundations of modern stereo vision systems, with a focus on how 3D structure and human-inspired perception contribute to accurate depth reconstruction. We revisit the Cyclopean Eye model and propose novel geometric constraints that account for occlusions and depth discontinuities. Our analysis includes the evaluation of stereo feature matching quality derived from deep learning models, as well as the role of attention mechanisms in recovering meaningful 3D surfaces. Through both theoretical insights and empirical studies on real datasets, we demonstrate that combining strong geometric priors with learned features provides internal abstractions for understanding stereo vision systems.
Overview
In this paper we study the importance of the cyclopean eye in stereo vision, presenting how occlusions, textureless/homogeneous regions, and repetitive patterns are interpreted by the modern Deep Learning (DL) stereo-vision approaches.
Also, we discuss the cyclopean view on the human perception perspective, and how it can be used to improve the DL stereo-vision systems.
Paper
The Role of Cyclopean-Eye in Stereo Vision
Sherlon Almeida da Silva, Davi Geiger, Luiz Velho, and Moacir Antonelli Ponti
If you have any questions, please reach out to Sherlon Almeida: sherlon@usp.br.
Citation
@inproceedings {
dasilva2025stereo,
title={The Role of Cyclopean-Eye in Stereo Vision},
author={da Silva, Sherlon Almeida and Geiger, Davi and Velho, Luiz and Ponti, Moacir Antonelli},
booktitle={Iberoamerican Congress on Pattern Recognition},
year={2025},
organization={Springer}
}