Documents
Presentation Slides
Presentation Slides
Mondrian Stereo
- Citation Author(s):
- Submitted by:
- Dylan Quenneville
- Last updated:
- 20 September 2017 - 1:18pm
- Document Type:
- Presentation Slides
- Document Year:
- 2017
- Event:
- Presenters:
- Dylan Quenneville
- Paper Code:
- MA-L5.4
- Categories:
- Log in to post comments
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.