Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
Authors:
- He WangHe Wang
- Edmond S. L. HoEHEdmond S. L. Ho
- Hubert P. H. ShumHSHubert P. H. Shum
Preprint
Abstract
Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. Recent research has shown that such problems can be approached by learning a natural motion manifold using deep learning to address the shortcomings of traditional data-driven approaches. However, previous methods can be sub-optimal for two reasons. First, the skeletal information has not been fully utilized for feature extraction. Unlike images, it is difficult to define spatial proximity in skeletal motions in the way that deep networks can be applied. Second, motion is time-series data with strong multi-modal temporal correlations. A frame could be followed by several candidate frames leading to different motions; long-range dependencies exist where a number of frames in the beginning correlate to a number of frames later. Ineffective modeling would either under-estimate the multi-modality and variance, resulting in featureless mean motion or over-estimate them resulting in jittery motions. In this paper, we propose a new deep network to tackle these challenges by creating a natural motion manifold that is versatile for many applications. The network has a new spatial component for feature extraction. It is also equipped with a new batch prediction model that predicts a large number of frames at once, such that long-term temporally-based objective functions can be employed to correctly learn the motion multi-modality and variances. With our system, long-duration motions can be predicted/synthesized using an open-loop setup where the motion retains the dynamics accurately. It can also be used for denoising corrupted motions and synthesizing new motions with given control signals. We demonstrate that our system can create superior results comparing to existing work in multiple applications.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- On Human Motion Prediction Using Recurrent Neural Networks2017
- Kinect Posture Reconstruction Based on a Local Mixture of Gaussian Process ModelsIEEE Transactions on Visualization and Computer Graphics, 2015
- Controllable data sampling in the space of human posesComputer Animation and Virtual Worlds, 2015
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Real-Time Posture Reconstruction for Microsoft KinectIEEE Transactions on Cybernetics, 2013
- Motion reconstruction using sparse accelerometer dataACM Transactions on Graphics, 2011
- Natural Character Posing from a Large Motion DatabaseIEEE Computer Graphics and Applications, 2011
- Example-Based Human Motion DenoisingIEEE Transactions on Visualization and Computer Graphics, 2010
- Spectral‐Based Group Formation ControlComputer Graphics Forum, 2009
- Key Object Driven Multi-category Object Recognition, Localization and Tracking Using Spatio-temporal Context2008