Single-shot 3D multi-person pose estimation in complex images
arXiv:1911.03391 · doi:10.1016/j.patcog.2020.107534
Abstract
In this paper, we propose a new single shot method for multi-person 3D human pose estimation in complex images. The model jointly learns to locate the human joints in the image, to estimate their 3D coordinates and to group these predictions into full human skeletons. The proposed method deals with a variable number of people and does not need bounding boxes to estimate the 3D poses. It leverages and extends the Stacked Hourglass Network and its multi-scale feature learning to manage multi-person situations. Thus, we exploit a robust 3D human pose formulation to fully describe several 3D human poses even in case of strong occlusions or crops. Then, joint grouping and human pose estimation for an arbitrary number of people are performed using the associative embedding method. Our approach significantly outperforms the state of the art on the challenging CMU Panoptic and a previous single shot method on the MuPoTS-3D dataset. Furthermore, it leads to good results on the complex and synthetic images from the newly proposed JTA Dataset.
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Learning from Synthetic Humans
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
- MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
- Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
Cited by in corpus (5)
- MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
- EfficientPose: Scalable single-person pose estimation
- Deep learning for 3D human pose estimation and mesh recovery: A survey
- NIMBLE: A Non-rigid Hand Model with Bones and Muscles
- PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation