Learning 3D Human Dynamics from Video

From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of humans in motion. We present a framework that can similarly learn a representation of 3D dynamics of humans from video via a simple but effective temporal encoding of image features. At test time, from video, the learned temporal representation give rise to smooth 3D mesh predictions. From a single image, our model can recover the current 3D mesh as well as its 3D past and future motion. Our approach is designed so it can learn from videos with 2D pose annotations in a semi-supervised manner. Though annotated data is always limited, there are millions of videos uploaded daily on the Internet. In this work, we harvest this Internet-scale source of unlabeled data by training our model on unlabeled video with pseudo-ground truth 2D pose obtained from an off-the-shelf 2D pose detector. Our experiments show that adding more videos with pseudo-ground truth 2D pose monotonically improves 3D prediction performance. We evaluate our model, Human Mesh and Motion Recovery (HMMR), on the recent challenging dataset of 3D Poses in the Wild and obtain state-of-the-art performance on the 3D prediction task without any fine-tuning. The project website with video, code, and data can be found at https://akanazawa.github.io/human_dynamics/.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper

Ranked #15 on 3D Human Pose Estimation on 3DPW (Acceleration Error metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation 3DPW HMMR (T=20) PA-MPJPE 72.6 # 116
MPJPE 116.5 # 102
Acceleration Error 15.2 # 15
3D Human Pose Estimation Human3.6M HMMR (T=20) Average MPJPE (mm) 83.7 # 295
PA-MPJPE 56.9 # 102


No methods listed for this paper. Add relevant methods here