Quasi-Dense 3D Reconstruction Using Tensor-Based Multiview Stereo
Abstract
We propose tensor-based multiview stereo (TMVS) for quasi-dense 3D reconstruction from uncalibrated images. Our work is inspired by the patch-based multiview stereo (PMVS), a state-of-the-art technique in multiview stereo reconstruction. The effectiveness of PMVS is attributed to the use of 3D patches in the match-propagate-filter MVS pipeline. Our key observation is: PMVS has not fully utilized the valuable 3D geometric cue available in 3D patches which are oriented points. This paper combines the complementary advantages of photoconsistency, visibility and geometric consistency enforcement in MVS via the use of 3D tensors, where our closed-form solution to tensor voting provides a unified approach to implement the match-propagate-filter pipeline. Using PMVS as the implementation backbone where TMVS is built, we provide qualitative and quantitative evaluation to demonstrate how TMVS significantly improve the MVS pipeline. ©2010 IEEE.
Cite
Text
Wu et al. "Quasi-Dense 3D Reconstruction Using Tensor-Based Multiview Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539796Markdown
[Wu et al. "Quasi-Dense 3D Reconstruction Using Tensor-Based Multiview Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/wu2010cvpr-quasi/) doi:10.1109/CVPR.2010.5539796BibTeX
@inproceedings{wu2010cvpr-quasi,
title = {{Quasi-Dense 3D Reconstruction Using Tensor-Based Multiview Stereo}},
author = {Wu, Tai-Pang and Yeung, Sai Kit and Jia, Jiaya and Tang, Chi-Keung},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {1482-1489},
doi = {10.1109/CVPR.2010.5539796},
url = {https://mlanthology.org/cvpr/2010/wu2010cvpr-quasi/}
}