Deep Generative Modelling of Human Reach-and-Place Action

TL;DR

This paper introduces a simple convolutional deep generative model for human reach-and-place actions that efficiently produces diverse 3D motion sequences conditioned on start and end positions, capturing natural variation.

Contribution

It presents a novel convolutional approach with temporal encoding for generating human motion, simplifying previous complex models like RNNs.

Findings

The model generates diverse 3D motions conditioned on start and end points.

It produces complete motion sequences in linear time.

Evaluation shows effective diversity and applicability of the generated motions.

Abstract

The motion of picking up and placing an object in 3D space is full of subtle detail. Typically these motions are formed from the same constraints, optimizing for swiftness, energy efficiency, as well as physiological limits. Yet, even for identical goals, the motion realized is always subject to natural variation. To capture these aspects computationally, we suggest a deep generative model for human reach-and-place action, conditioned on a start and end position.We have captured a dataset of 600 such human 3D actions, to sample the 2x3-D space of 3D source and targets. While temporal variation is often modeled with complex learning machinery like recurrent neural networks or networks with memory or attention, we here demonstrate a much simpler approach that is convolutional in time and makes use of(periodic) temporal encoding. Provided a latent code and conditioned on start and end position, the model generates a complete 3D character motion in linear time as a sequence of convolutions. Our evaluation includes several ablations, analysis of generative diversity and applications.