VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera

We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e. it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M VNect (Augm.) Average MPJPE (mm) 80.5 # 291
3D Human Pose Estimation MPI-INF-3DHP VNect (ResNet 50 GT) AUC 41.6 # 61
PCK 79.4 # 63
3D Human Pose Estimation MPI-INF-3DHP VNect (Augm.) AUC 40.4 # 66
MPJPE 124.7 # 83
PCK 76.6 # 70

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Pose Estimation Leeds Sports Poses VNect (ResNet 50) PCK 79.4 # 16

Methods


No methods listed for this paper. Add relevant methods here