Displets: Resolving Stereo Ambiguities using Object Knowledge
Stereo techniques have witnessed tremendous progress over the last decades, yet some aspects of the problem still remain challenging today. Striking examples are reflecting and textureless surfaces which cannot easily be recovered using traditional local regularizers. In this paper, we therefore propose to regularize over larger distances using object-category specific disparity proposals (displets) which we sample using inverse graphics techniques based on a sparse disparity estimate and a semantic segmentation of the image. The proposed displets encode the fact that objects of certain categories are not arbitrarily shaped but typically exhibit regular structures. We integrate them as non-local regularizer for the challenging object class 'car' into a superpixel based CRF framework and demonstrate its benefits on the KITTI stereo evaluation.
| Author(s): | Fatma Güney and Andreas Geiger |
| Book Title: | IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015 |
| Pages: | 4165--4175 |
| Year: | 2015 |
| Month: | June |
| Bibtex Type: | Conference Paper (inproceedings) |
| Event Name: | IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2015 |
| Event Place: | Boston, MA, USA |
| Electronic Archiving: | grant_archive |
| Links: | |
BibTex
@inproceedings{Guney2015CVPR,
title = {Displets: Resolving Stereo Ambiguities using Object Knowledge},
booktitle = { IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015},
abstract = {Stereo techniques have witnessed tremendous progress over the last decades, yet some aspects of the problem still remain challenging today. Striking examples are reflecting and textureless surfaces which cannot easily be recovered using traditional local regularizers. In this paper, we therefore propose to regularize over larger distances using object-category specific disparity proposals (displets) which we sample using inverse graphics techniques based on a sparse disparity estimate and a semantic segmentation of the image. The proposed displets encode the fact that objects of certain categories are not arbitrarily shaped but typically exhibit regular structures. We integrate them as non-local regularizer for the challenging object class 'car' into a superpixel based CRF framework and demonstrate its benefits on the KITTI stereo evaluation.},
pages = {4165--4175},
month = jun,
year = {2015},
slug = {guney2015cvpr},
author = {G{\"u}ney, Fatma and Geiger, Andreas},
month_numeric = {6}
}