Exploring the Effect of Sampling Strategy on Movement Generation with Generative Neural Networks
Lists
Only you see this
Abstract
It is common to explore multiple sampling approaches when generating output from generative deep neural networks for creative applications.<br> Choosing suitable sampling parameters can make or break the realism and perceived creative merit of the output. This is particularly important when attempting to simulate variations of expressive human movement. The process of selecting the correct sampling parameters is often task-specific and under-reported in many publications, which can make the reproducibility of the results challenging.<br> We explore some of the most common sampling techniques in the context of generating human body movement, specifically dance movement, and attempt to shine a light on their advantages and limitations.<br> This work presents a Mixture Density Recurrent Neural Network trained on a dataset of improvised dance motion capture data from which it is possible to generate novel movement sequences.<br> Systematically examining the different sampling strategies allows us to further the understanding of how the sampling parameters affect motion generation, which provides evidence for utility in creative applications.
BibTeX
@inproceedings{wallace2020exploring,
author = {Benedikte Wallace and Kristian Nymoen and Charles Martín and Jim Toressen},
title = {{Exploring the Effect of Sampling Strategy on Movement Generation with Generative Neural Networks}},
booktitle = {Zenodo},
year = {2020},
doi = {10.5281/zenodo.4024477},
}Loading related content...