Back to Search
Start Over
Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation.
- Source :
- IEEE Transactions on Pattern Analysis & Machine Intelligence; Oct2022, Vol. 44 Issue 10, p6327-6344, 18p
- Publication Year :
- 2022
-
Abstract
- In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation from a monocular RGB image. Our model takes estimated 2D pose as the input and learns a generalized 2D-3D mapping function to leverage into 3D pose. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNNs) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a data augmentation algorithm to further improve model robustness against appearance variations and cross-view generalization ability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges. [ABSTRACT FROM AUTHOR]
- Subjects :
- DATA augmentation
MONOCULARS
ARTIFICIAL neural networks
GRAMMAR
MOTOR ability
Subjects
Details
- Language :
- English
- ISSN :
- 01628828
- Volume :
- 44
- Issue :
- 10
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Pattern Analysis & Machine Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 159210551
- Full Text :
- https://doi.org/10.1109/TPAMI.2021.3087695