Ego-Pose Estimation and Forecasting as Real-Time PD Control
arXiv:1906.03173
Abstract
We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos. The method learns directly from unsegmented egocentric videos and motion capture data consisting of various complex human motions (e.g., crouching, hopping, bending, and motion transitions). We propose a video-conditioned recurrent control technique to forecast physically-valid and stable future motions of arbitrary length. We also introduce a value function based fail-safe mechanism which enables our method to run as a single pass algorithm over the video data. Experiments with both controlled and in-the-wild data show that our approach outperforms previous art in both quantitative metrics and visual quality of the motions, and is also robust enough to transfer directly to real-world scenarios. Additionally, our time analysis shows that the combined use of our pose estimation and forecasting can run at 30 FPS, making it suitable for real-time applications.
arXiv commentICCV 2019; Webpage: https://www.ye-yuan.com/ego-pose; Video: https://youtu.be/968IIDZeWE0
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
- MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
- Learning human behaviors from motion capture by adversarial imitation
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
- Learning 3D Human Dynamics from Video
- Learning 3D Human Pose from Structure and Motion