A Neural Network Model of 3-D Lightness Perception
Abstract
A neural network model of 3-D lightness perception is presented which builds upon the FACADE Theory Boundary Contour Sys(cid:173) tem/Feature Contour System of Grossberg and colleagues. Early ratio encoding by retinal ganglion neurons as well as psychophysi(cid:173) cal results on constancy across different backgrounds (background constancy) are used to provide functional constraints to the theory and suggest a contrast negation hypothesis which states that ratio measures between coplanar regions are given more weight in the determination of lightness of the respective regions. Simulations of the model address data on lightness perception, including the coplanar ratio hypothesis, the Benary cross, and White's illusion.
Cite
Text
Pessoa and Ross. "A Neural Network Model of 3-D Lightness Perception." Neural Information Processing Systems, 1995.Markdown
[Pessoa and Ross. "A Neural Network Model of 3-D Lightness Perception." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/pessoa1995neurips-neural/)BibTeX
@inproceedings{pessoa1995neurips-neural,
title = {{A Neural Network Model of 3-D Lightness Perception}},
author = {Pessoa, Luiz and Ross, William D.},
booktitle = {Neural Information Processing Systems},
year = {1995},
pages = {844-850},
url = {https://mlanthology.org/neurips/1995/pessoa1995neurips-neural/}
}