Human Motion Prediction via Spatio-Temporal Inpainting

Abstract

We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively short periods of time (few hundred milliseconds) and typically ignore the absolute position of the skeleton w.r.t. the camera. Our scheme provides long term predictions (two seconds or more) for both the body pose and its absolute position. Our approach builds upon three main contributions. First, we represent the data using a spatiotemporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well. Secondly, we design an architecture to learn the joint distribution of body poses and global motion, capable to hypothesize large chunks of the input 3D tensor with missing data. And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. We propose two alternative metrics, based on the distribution of frequencies, that are able to capture more realistic motion patterns. Extensive experiments demonstrate our approach to significantly improve the state of the art, while also handling situations in which past observations are corrupted by occlusions, noise and missing frames.

DLow: Diversifying Latent Flows for Diverse Human Motion Prediction

“…More related to our work, stochastic human motion prediction methods start to gain popularity with the development of deep generative models. These methods [68,46,6,61,42,71,3] often build upon popular generative models such as conditional generative adversarial networks (CGANs; [21]) or conditional variational autoencoders (CVAEs; [38]). The aforementioned methods differ in the design of their generative models, but at test time they follow the same sampling strategy -randomly and independently sampling trajectories from the pretrained generative model without considering the correlation between samples.…”

“…Deep generative models, e.g., variational autoencoders (VAEs) [38], are effective tools to model multi-modal data distributions. Most existing work [68,46,6,61,42,71,3] using deep generative models for human motion prediction is focused on the design of the generative model to allow it to effectively learn the data distribution. After the generative model is learned, little attention has been paid to the sampling method used to produce motion samples (predicted future motions) from the pretrained generative model (weights kept fixed).…”

Inertial sensor based human behavior recognition in modal testing using machine learning approach

“…It learns a function based on samples of input data and desired outputs and approximates a function between input and output. Researchers have used machine learning successfully for recognition of human motions/behavior [17][18][19][20][21]. In a recent study conducted by Wang et al [22], supervised machine learning is used to learn structures of different three-dimensional (3D) human poses.…”