ML Anthology

Discriminatively Trained Dense Surface Normal Estimation

Lubor Ladicky, Bernhard Zeisl, Marc Pollefeys
ECCV 2014 pp. 468-484
doi:10.1007/978-3-319-10602-1_31 /eccv/2014/ladicky2014eccv-discriminatively/

Abstract

In this work we propose the method for a rather unexplored problem of computer vision - discriminatively trained dense surface normal estimation from a single image. Our method combines contextual and segment-based cues and builds a regressor in a boosting framework by transforming the problem into the regression of coefficients of a local coding. We apply our method to two challenging data sets containing images of man-made environments, the indoor NYU2 data set and the outdoor KITTI data set. Our surface normal predictor achieves results better than initially expected, significantly outperforming state-of-the-art.

PDF ECCV Semantic Scholar

Cite

Text

Ladicky et al. "Discriminatively Trained Dense Surface Normal Estimation." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10602-1_31

Markdown

[Ladicky et al. "Discriminatively Trained Dense Surface Normal Estimation." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/ladicky2014eccv-discriminatively/) doi:10.1007/978-3-319-10602-1_31

BibTeX

@inproceedings{ladicky2014eccv-discriminatively,
  title     = {{Discriminatively Trained Dense Surface Normal Estimation}},
  author    = {Ladicky, Lubor and Zeisl, Bernhard and Pollefeys, Marc},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {468-484},
  doi       = {10.1007/978-3-319-10602-1_31},
  url       = {https://mlanthology.org/eccv/2014/ladicky2014eccv-discriminatively/}
}