Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data
Abstract
We address the problem of segmenting 3D scan data into objects or object classes. Our segmentation framework is based on a subclass of Markov random fields (MRFs) which support efficient graph-cut inference. The MRF models incorporate a large set of diverse features and enforce the preference that adjacent scan points have the same classification label. We use a recently proposed maximum-margin framework to discriminatively train the model from a set of labeled scans; as a result we automatically learn the relative importance of the features for the segmentation task. Performing graph-cut inference in the trained MRF can then be used to segment new scenes very efficiently. We test our approach on three large-scale datasets produced by different kinds of 3D sensors, showing its applicability to both outdoor and indoor environments containing diverse objects.
Cite
Text
Anguelov et al. "Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.133Markdown
[Anguelov et al. "Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/anguelov2005cvpr-discriminative/) doi:10.1109/CVPR.2005.133BibTeX
@inproceedings{anguelov2005cvpr-discriminative,
title = {{Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data}},
author = {Anguelov, Dragomir and Taskar, Benjamin and Chatalbashev, Vassil and Koller, Daphne and Gupta, Dinkar and Heitz, Geremy and Ng, Andrew Y.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2005},
pages = {169-176},
doi = {10.1109/CVPR.2005.133},
url = {https://mlanthology.org/cvpr/2005/anguelov2005cvpr-discriminative/}
}