Structure recovery by part assembly
Chao-Hui Shen, Hongbo Fu, Kang Chen, Shi-Min Hu
In ACM Transactions on Graphics, 31(6), November 2012.
Abstract: This paper presents a technique that allows quick conversion of acquired low-quality data from consumer-level scanning devices to high-quality 3D models with labeled semantic parts and meanwhile their assembly reasonably close to the underlying geometry. This is achieved by a novel structure recovery approach that is essentially local to global and bottom up, enabling the creation of new structures by assembling existing labeled parts with respect to the acquired data. We demonstrate that using only a small-scale shape repository, our part assembly approach is able to faithfully recover a variety of high-level structures from only a single-view scan of man-made objects acquired by the Kinect system, containing a highly noisy, incomplete 3D point cloud and a corresponding RGB image.
Article URL: http://dx.doi.org/10.1145/2366145.2366199
BibTeX format:
@article{Shen:2012:SRB,
  author = {Chao-Hui Shen and Hongbo Fu and Kang Chen and Shi-Min Hu},
  title = {Structure recovery by part assembly},
  journal = {ACM Transactions on Graphics},
  volume = {31},
  number = {6},
  pages = {180:1--180:11},
  month = nov,
  year = {2012},
}
Search for more articles by Chao-Hui Shen.
Search for more articles by Hongbo Fu.
Search for more articles by Kang Chen.
Search for more articles by Shi-Min Hu.

Return to the search page.


graphbib: Powered by "bibsql" and "SQLite3."