Direct Structure Estimation for 3D Reconstruction

Nianjuan Jiang, Daniel Lin, Minh N. Do, Jiangbo Lu

CVPR 2015

doi:10.1109/CVPR.2015.7298881 /cvpr/2015/jiang2015cvpr-direct/

Abstract

Most conventional structure-from-motion (SFM) techniques require camera pose estimation before computing any scene structure. In this work we show that when combined with single/multiple homography estimation, the general Euclidean rigidity constraint provides a simple formulation for scene structure recovery without explicit camera pose computation. This direct structure estimation (DSE) opens a new way to design a SFM system that reverses the order of structure and motion estimation. We show that this alternative approach works well for recovering scene structure and camera poses from sideway motion given planar or general man-made scenes.

PDF CVPR Semantic Scholar

Cite

Text

Jiang et al. "Direct Structure Estimation for 3D Reconstruction." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298881

Markdown

[Jiang et al. "Direct Structure Estimation for 3D Reconstruction." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/jiang2015cvpr-direct/) doi:10.1109/CVPR.2015.7298881

BibTeX

@inproceedings{jiang2015cvpr-direct,
  title     = {{Direct Structure Estimation for 3D Reconstruction}},
  author    = {Jiang, Nianjuan and Lin, Daniel and Do, Minh N. and Lu, Jiangbo},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298881},
  url       = {https://mlanthology.org/cvpr/2015/jiang2015cvpr-direct/}
}