Robust Reconstruction of Indoor Scenes

Sungjoon Choi, Qian-Yi Zhou, Vladlen Koltun

CVPR 2015

doi:10.1109/CVPR.2015.7299195 /cvpr/2015/choi2015cvpr-robust/

Abstract

We present an approach to indoor scene reconstruction from RGB-D video. The key idea is to combine geometric registration of scene fragments with robust global optimization based on line processes. Geometric registration is error-prone due to sensor noise, which leads to aliasing of geometric detail and inability to disambiguate different surfaces in the scene. The presented optimization approach disables erroneous geometric alignments even when they significantly outnumber correct ones. Experimental results demonstrate that the presented approach substantially increases the accuracy of reconstructed scene models.

PDF CVPR Semantic Scholar

Cite

Text

Choi et al. "Robust Reconstruction of Indoor Scenes." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299195

Markdown

[Choi et al. "Robust Reconstruction of Indoor Scenes." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/choi2015cvpr-robust/) doi:10.1109/CVPR.2015.7299195

BibTeX

@inproceedings{choi2015cvpr-robust,
  title     = {{Robust Reconstruction of Indoor Scenes}},
  author    = {Choi, Sungjoon and Zhou, Qian-Yi and Koltun, Vladlen},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299195},
  url       = {https://mlanthology.org/cvpr/2015/choi2015cvpr-robust/}
}