Abstract
We develop a novel approach to generate human body models in a variety of shapes and poses via tuning semantic parameters. Our approach is investigated with datasets of up to 3000 scanned body models which have been placed in point to point correspondence. Correspondence is established by nonrigid deformation of a template mesh. The large dataset allows a local model to be learned robustly, in which individual parts of the human body can be accurately reshaped according to semantic parameters. We evaluate performance on two datasets and find that our model outperforms existing methods.
Original language | English |
---|---|
Title of host publication | Proceedings - 2014 International Conference on 3D Vision Workshops, 3DV 2014 |
Pages | 41-48 |
Number of pages | 8 |
ISBN (Electronic) | 9781479970018 |
DOIs | |
State | Published - Aug 7 2015 |
Event | 2nd International Conference on 3D Vision Workshops, 3DV 2014 - Tokyo, Japan Duration: Dec 8 2014 → Dec 11 2014 |
Publication series
Name | Proceedings - 2014 International Conference on 3D Vision Workshops, 3DV 2014 |
---|
Conference
Conference | 2nd International Conference on 3D Vision Workshops, 3DV 2014 |
---|---|
Country/Territory | Japan |
City | Tokyo |
Period | 12/8/14 → 12/11/14 |
Bibliographical note
Publisher Copyright:© 2014 IEEE.
Keywords
- deformation
- local mapping
- reshaping
- semantic parameters
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Signal Processing
- Radiology Nuclear Medicine and imaging