ML Anthology

3-D Scene Representation with Layered Non-Uniform Global Sampling

Huei-Yung Lin, Yu-Hua Xiao
CVPRW 2010 pp. 51-56
doi:10.1109/CVPRW.2010.5543805 /cvprw/2010/lin2010cvprw-3d/

Abstract

The representation of a 3-D scene is essential to recent multi-view imaging technologies. In this paper we propose a unified geometry and texture representation based on global resampling of the scene. The 3-D coordinates and the associated texture information of the scene points are represented in the polar coordinate system. A novel layered data map representation with distance-dependent nonuniform sampling strategy is proposed to deal with complex scenes. It is capable of increasing the details of the 3-D structure locally and thus is compact in size. The experimental results on synthetic data sets and real images are presented.

CVPRW Semantic Scholar

Cite

Text

Lin and Xiao. "3-D Scene Representation with Layered Non-Uniform Global Sampling." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010. doi:10.1109/CVPRW.2010.5543805

Markdown

[Lin and Xiao. "3-D Scene Representation with Layered Non-Uniform Global Sampling." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010.](https://mlanthology.org/cvprw/2010/lin2010cvprw-3d/) doi:10.1109/CVPRW.2010.5543805

BibTeX

@inproceedings{lin2010cvprw-3d,
  title     = {{3-D Scene Representation with Layered Non-Uniform Global Sampling}},
  author    = {Lin, Huei-Yung and Xiao, Yu-Hua},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2010},
  pages     = {51-56},
  doi       = {10.1109/CVPRW.2010.5543805},
  url       = {https://mlanthology.org/cvprw/2010/lin2010cvprw-3d/}
}