Back to Search
Start Over
Weakly supervised 2D human pose transfer.
- Source :
- SCIENCE CHINA Information Sciences; Nov2021, Vol. 64 Issue 11, p1-17, 17p
- Publication Year :
- 2021
-
Abstract
- We present a novel method for pose transfer between two 2D human skeletons. When the bone lengths and proportions between the two skeletons are significantly different, pose transfer becomes a challenging task, which cannot be accomplished by simply copying the joint positions or the bone directions. Our data-driven approach utilizes a deep neural network trained, in a weakly supervised fashion, to encode a skeleton into two separate latent codes, one representing its pose, and another representing the skeleton’s proportions (skeleton-ID). The network is given two skeletons, and learns to combine the pose of one with the skeleton-ID of the other. Lacking supervision on the poses, we develop a novel loss that qualitatively compares poses of different skeletons. We evaluate the performance of our method on a large set of poses. The advantages of avoiding supervision are demonstrated by showing transfer of extreme poses, as well as between uncommon skeleton proportions. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 1674733X
- Volume :
- 64
- Issue :
- 11
- Database :
- Complementary Index
- Journal :
- SCIENCE CHINA Information Sciences
- Publication Type :
- Academic Journal
- Accession number :
- 153354131
- Full Text :
- https://doi.org/10.1007/s11432-021-3301-5