Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling

by   Edmond S. L. Ho, et al.

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.


page 4

page 7

page 9

page 12


Human Motion Prediction Using Manifold-Aware Wasserstein GAN

Human motion prediction aims to forecast future human poses given a prio...

3D Skeleton-based Human Motion Prediction with Manifold-Aware GAN

In this work we propose a novel solution for 3D skeleton-based human mot...

Generative Tweening: Long-term Inbetweening of 3D Human Motions

The ability to generate complex and realistic human body animations at s...

Constructing Human Motion Manifold with Sequential Networks

This paper presents a novel recurrent neural network-based method to con...

A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions

Motion estimation is one of the core challenges in computer vision. With...

Correspondence-free online human motion retargeting

We present a novel data-driven framework for unsupervised human motion r...

Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns

Dynamic patterns are characterized by complex spatial and motion pattern...

Please sign up or login with your details

Forgot password? Click here to reset