Perceiving Systems, Computer Vision

Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape from Images

2018

Conference Paper

ps


Animals are widespread in nature and the analysis of their shape and motion is important in many fields and industries. Modeling 3D animal shape, however, is difficult because the 3D scanning methods used to capture human shape are not applicable to wild animals or natural settings. Consequently, we propose a method to capture the detailed 3D shape of animals from images alone. The articulated and deformable nature of animals makes this problem extremely challenging, particularly in unconstrained environments with moving and uncalibrated cameras. To make this possible, we use a strong prior model of articulated animal shape that we fit to the image data. We then deform the animal shape in a canonical reference pose such that it matches image evidence when articulated and projected into multiple images. Our method extracts significantly more 3D shape detail than previous methods and is able to model new species, including the shape of an extinct animal, using only a few video frames. Additionally, the projected 3D shapes are accurate enough to facilitate the extraction of a realistic texture map from multiple frames.

Author(s): Silvia Zuffi and Angjoo Kanazawa and Michael J. Black
Book Title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Pages: 3955-3963
Year: 2018
Publisher: IEEE Computer Society

Department(s): Perceiving Systems
Research Project(s): Animal Shape and Pose
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1109/CVPR.2018.00416
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Event Place: Salt Lake City, USA

Links: pdf
code/data
3D models

BibTex

@inproceedings{Zuffi:CVPR:2018,
  title = {Lions and Tigers and Bears: Capturing Non-Rigid, {3D}, Articulated Shape from Images},
  author = {Zuffi, Silvia and Kanazawa, Angjoo and Black, Michael J.},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {3955-3963},
  publisher = {IEEE Computer Society},
  year = {2018},
  doi = {10.1109/CVPR.2018.00416}
}