Image library for unsupervised learning of depth from stereo

Lies, P; Bethge, M

doi:10.3389/conf.neuro.10.2008.01.083

Local TagsStatisticsRelease HistoryDetailsSummary

Image library for unsupervised learning of depth from stereo

Lies, P., & Bethge, M. (2008). Image library for unsupervised learning of depth from stereo. Poster presented at Bernstein Symposium 2008, München, Germany.

Item is Released

show all hide all

Basic

show hide

Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C6DB-D Version Permalink: http://hdl.handle.net/21.11116/0000-0003-8B8A-5

Genre: Poster

Files

show Files

Locators

show

hide

Locator:
https://www.frontiersin.org/10.3389/conf.neuro.10.2008.01.083/event_abstract (Publisher version)

Description:
-

Creators

show

hide

Creators:
Lies, P^{1, 2}, Author
Bethge, M^{1, 2}, Author

Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: The visual system is able to extract depth information from the disparity of the two images on the retinae. Every system that makes use of disparity information must identify corresponding points in the two images. This correspondence problem constitutes a principal difficulty in depth from stereo and many questions are left open about how the visual system solves it. In this work, we seek to understand how depth inference can emerge from unsupervised learning of statistical regularities in binocular images. In a first step we acquire a database of training data by using virtual 3D sceneries which are rendered into stereo images from two eye-like positioned cameras. This provides us with an extensive repository of stereo images along with precise depth and disparity maps. In the future we will use this data as ground truth for a quantitative analysis and comparison of different models for depth inference.

Details

show

hide

Language(s):

Dates: Published in Print: 2008-11

Publication Status: Published in print

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: DOI: 10.3389/conf.neuro.10.2008.01.083
BibTex Citekey: 5532

Degree: -

Event

show

hide

Title: Bernstein Symposium 2008

Place of Event: München, Germany

Start-/End Date: 2008-10-08 - 2008-10-10

Legal Case

show

Project information

show

Source 1

show

hide

Title: Frontiers in Computational Neuroscience

Abbreviation : Front Comput Neurosci

Source Genre: Journal

Creator(s):

Affiliations:

Publ. Info: Lausanne : Frontiers Research Foundation

Pages: - Volume / Issue: 2008 (Conference Abstract: Bernstein Symposium 2008) Sequence Number: - Start / End Page: - Identifier: Other: 1662-5188
CoNE: https://pure.mpg.de/cone/journals/resource/1662-5188