Relative 3D Regularized B-Spline Surface Reconstruction Through Image Sequences
Abstract
This paper considers the problem of 3D surface reconstruction using image sequences. We propose a direct method of surface reconstruction which is based on regularized uniform bicubic B-spline surface patches. The reconstruction is achieved by observing the motion of occluding contours [1, 4, 10], i.e., where the view lines graze the surface. It has been shown that reconstruction of such a 3D surface is possible when the camera motion is known, with the exception of those fully concave parts where no view line can be tangential to the surface. This approach differs from previous work, it states directly the problem of regularization on the 3D surface. Experimental results are presented for real data.
Cite
Text
Zhao and Mohr. "Relative 3D Regularized B-Spline Surface Reconstruction Through Image Sequences." European Conference on Computer Vision, 1994. doi:10.1007/BFB0028373Markdown
[Zhao and Mohr. "Relative 3D Regularized B-Spline Surface Reconstruction Through Image Sequences." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/zhao1994eccv-relative/) doi:10.1007/BFB0028373BibTeX
@inproceedings{zhao1994eccv-relative,
title = {{Relative 3D Regularized B-Spline Surface Reconstruction Through Image Sequences}},
author = {Zhao, Changsheng and Mohr, Roger},
booktitle = {European Conference on Computer Vision},
year = {1994},
pages = {417-426},
doi = {10.1007/BFB0028373},
url = {https://mlanthology.org/eccv/1994/zhao1994eccv-relative/}
}