Presentation | 1994/6/28 A neural network model of surface reconstruction from binocular disparity Nobuhiko Asakura, Toshio Inui, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We investigated the process of surface reconstruction from binocular disparity in the framework of regularization and Markov Random Field theory.First,we reformulated 2-coupled MRF models to propose a new model in which the reliability of given disparities is used to obtain,optimal surface reconstructions.Then,we illustrated the neural network implementation and showed the numerical examples such as MTF and Craik O′Brien effect for visual depth.Finally,we pointed out a close relationship between our formulation and the curvature disparity hypothesis proposed by Rogers and Cagenello(1989). |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | binocular disparity / surface reconstruction / Markor Random Field / Craik O′Brien effect |
Paper # | NC94-21 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1994/6/28(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A neural network model of surface reconstruction from binocular disparity |
Sub Title (in English) | |
Keyword(1) | binocular disparity |
Keyword(2) | surface reconstruction |
Keyword(3) | Markor Random Field |
Keyword(4) | Craik O′Brien effect |
1st Author's Name | Nobuhiko Asakura |
1st Author's Affiliation | Department of Psychology,Faculty of Letters,Kyoto University() |
2nd Author's Name | Toshio Inui |
2nd Author's Affiliation | Department of Psychology,Faculty of Letters,Kyoto University |
Date | 1994/6/28 |
Paper # | NC94-21 |
Volume (vol) | vol.94 |
Number (no) | 129 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |