3D Human Pose Estimation with Siamese Equivariant Embedding
arXiv:1809.07217
Abstract
In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only.
arXiv commentAccepted to Neurocomputing
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Learning Face Representation by Joint Identification-Verification
- Siamese Regression Networks with Efficient mid-level Feature Extraction for 3D Object Pose Estimation
- It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
- FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information