Single-view reconstruction via joint analysis of image and shape collections
Qixing Huang, Hai Wang, Vladlen Koltun
In ACM Transactions on Graphics (TOG), 34(4), August 2015.
Abstract: We present an approach to automatic 3D reconstruction of objects depicted in Web images. The approach reconstructs objects from single views. The key idea is to jointly analyze a collection of images of different objects along with a smaller collection of existing 3D models. The images are analyzed and reconstructed together. Joint analysis regularizes the formulated optimization problems, stabilizes correspondence estimation, and leads to reasonable reproduction of object appearance without traditional multi-view cues.
Article URL: http://doi.acm.org/10.1145/2766890
BibTeX format:
@article{10.1145-2766890,
  author = {Qixing Huang and Hai Wang and Vladlen Koltun},
  title = {Single-view reconstruction via joint analysis of image and shape collections},
  journal = {ACM Transactions on Graphics (TOG)},
  volume = {34},
  number = {4},
  articleno = {87},
  month = aug,
  year = {2015},
}
Search for more articles by Qixing Huang.
Search for more articles by Hai Wang.
Search for more articles by Vladlen Koltun.

Return to the search page.


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