Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Mondrian Stereo

Abstract: 

Untextured scenes with complex occlusions still present challenges to modern stereo algorithms. We consider the pathological case of Mondrian Stereo—scenes consisting solely of solid-colored planar regions, inspired by paintings by Piet Mondrian. We analyze assumptions that allow disambiguating such scenes and present a novel stereo algorithm employing symbolic reasoning about matched edge segments. We demonstrate compelling stereo matching results on synthetic scenes and discuss how our insights could be utilized in robust real-world stereo algorithms for untextured environments.

up
0 users have voted:

Paper Details

Authors:
Daniel Scharstein
Submitted On:
20 September 2017 - 1:18pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Dylan Quenneville
Paper Code:
MA-L5.4
Document Year:
2017
Cite

Document Files

mondrian_stereo.pdf

(25 downloads)

Subscribe

[1] Daniel Scharstein, "Mondrian Stereo", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2241. Accessed: Oct. 23, 2017.
@article{2241-17,
url = {http://sigport.org/2241},
author = {Daniel Scharstein },
publisher = {IEEE SigPort},
title = {Mondrian Stereo},
year = {2017} }
TY - EJOUR
T1 - Mondrian Stereo
AU - Daniel Scharstein
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2241
ER -
Daniel Scharstein. (2017). Mondrian Stereo. IEEE SigPort. http://sigport.org/2241
Daniel Scharstein, 2017. Mondrian Stereo. Available at: http://sigport.org/2241.
Daniel Scharstein. (2017). "Mondrian Stereo." Web.
1. Daniel Scharstein. Mondrian Stereo [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2241