ML Anthology

Multi-Modal Scene Reconstruction Using Perceptual Grouping Constraints

Nicolas Pugeault, Florentin Wörgötter, Norbert Krüger
CVPRW 2006 pp. 195
doi:10.1109/CVPRW.2006.133 /cvprw/2006/pugeault2006cvprw-multimodal/

Abstract

In this work we propose a scheme integrating perceptual grouping into stereopsis to reduce the ambiguity of those early processes. We propose a simple perceptual grouping algorithm that - in addition to the geometric information makes use of a novel multi-modal affinity measure between local primitives. We then use this group information to 1) disambiguate the stereopsis by enforcing that stereo matches preserve groups; and 2) correct the reconstruction error due to the image pixel sampling using a linear interpolation over the groups. We show quantitative and qualitative demonstrations of those processes on a variety of sequences.

CVPRW Semantic Scholar

Cite

Text

Pugeault et al. "Multi-Modal Scene Reconstruction Using Perceptual Grouping Constraints." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006. doi:10.1109/CVPRW.2006.133

Markdown

[Pugeault et al. "Multi-Modal Scene Reconstruction Using Perceptual Grouping Constraints." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006.](https://mlanthology.org/cvprw/2006/pugeault2006cvprw-multimodal/) doi:10.1109/CVPRW.2006.133

BibTeX

@inproceedings{pugeault2006cvprw-multimodal,
  title     = {{Multi-Modal Scene Reconstruction Using Perceptual Grouping Constraints}},
  author    = {Pugeault, Nicolas and Wörgötter, Florentin and Krüger, Norbert},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2006},
  pages     = {195},
  doi       = {10.1109/CVPRW.2006.133},
  url       = {https://mlanthology.org/cvprw/2006/pugeault2006cvprw-multimodal/}
}