A Simple and Fast Neural Network Approach to Stereovision

Abstract

A neural network approach to stereovision is presented based on aliasing effects of simple disparity estimators and a fast coherence(cid:173) detection scheme. Within a single network structure, a dense dis(cid:173) parity map with an associated validation map and, additionally, the fused cyclopean view of the scene are available. The network operations are based on simple, biological plausible circuitry; the algorithm is fully parallel and non-iterative.

Cite

Text

Henkel. "A Simple and Fast Neural Network Approach to Stereovision." Neural Information Processing Systems, 1997.

Markdown

[Henkel. "A Simple and Fast Neural Network Approach to Stereovision." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/henkel1997neurips-simple/)

BibTeX

@inproceedings{henkel1997neurips-simple,
  title     = {{A Simple and Fast Neural Network Approach to Stereovision}},
  author    = {Henkel, Rolf D.},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {808-814},
  url       = {https://mlanthology.org/neurips/1997/henkel1997neurips-simple/}
}