GlocalNet: Class-aware Long-term Human Motion Synthesis

TL;DR

This paper introduces GlocalNet, a two-stage method for synthesizing long-term, class-aware human motion sequences that effectively captures complex temporal dependencies across diverse activities, outperforming existing methods.

Contribution

GlocalNet is the first approach to synthesize long-term human motion across over 50 activity classes using a two-stage process for global and dense trajectory generation.

Findings

Outperforms state-of-the-art methods on multiple metrics

Successfully synthesizes long-term (>6000 ms) motion sequences

Handles over 50 activity classes with high diversity

Abstract

Synthesis of long-term human motion skeleton sequences is essential to aid human-centric video generation with potential applications in Augmented Reality, 3D character animations, pedestrian trajectory prediction, etc. Long-term human motion synthesis is a challenging task due to multiple factors like, long-term temporal dependencies among poses, cyclic repetition across poses, bi-directional and multi-scale dependencies among poses, variable speed of actions, and a large as well as partially overlapping space of temporal pose variations across multiple class/types of human activities. This paper aims to address these challenges to synthesize a long-term (> 6000 ms) human motion trajectory across a large variety of human activity classes (>50). We propose a two-stage activity generation method to achieve this goal, where the first stage deals with learning the long-term global pose dependencies in activity sequences by learning to synthesize a sparse motion trajectory while the second stage addresses the generation of dense motion trajectories taking the output of the first stage. We demonstrate the superiority of the proposed method over SOTA methods using various quantitative evaluation metrics on publicly available datasets.