ML Anthology

Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures

Vaibhav Vaish, Marc Levoy, Richard Szeliski, C. Lawrence Zitnick, Sing Bing Kang
CVPR 2006 pp. 2331-2338
doi:10.1109/CVPR.2006.244 /cvpr/2006/vaish2006cvpr-reconstructing/

Abstract

Most algorithms for 3D reconstruction from images use cost functions based on SSD, which assume that the surfaces being reconstructed are visible to all cameras. This makes it difficult to reconstruct objects which are partially occluded. Recently, researchers working with large camera arrays have shown it is possible to "see through" occlusions using a technique called synthetic aperture focusing. This suggests that we can design alternative cost functions that are robust to occlusions using synthetic apertures. Our paper explores this design space. We compare classical shape from stereo with shape from synthetic aperture focus. We also describe two variants of multi-view stereo based on color medians and entropy that increase robustness to occlusions. We present an experimental comparison of these cost functions on complex light fields, measuring their accuracy against the amount of occlusion.

CVPR Semantic Scholar

Cite

Text

Vaish et al. "Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.244

Markdown

[Vaish et al. "Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/vaish2006cvpr-reconstructing/) doi:10.1109/CVPR.2006.244

BibTeX

@inproceedings{vaish2006cvpr-reconstructing,
  title     = {{Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures}},
  author    = {Vaish, Vaibhav and Levoy, Marc and Szeliski, Richard and Zitnick, C. Lawrence and Kang, Sing Bing},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {2331-2338},
  doi       = {10.1109/CVPR.2006.244},
  url       = {https://mlanthology.org/cvpr/2006/vaish2006cvpr-reconstructing/}
}