Neural Motion Compression with Frequency-adaptive Fourier Feature Network

Loading...
Thumbnail Image
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present a neural-network-based compression method to alleviate the storage cost of motion capture data. Human motions such as locomotion, often consist of periodic movements. We leverage this periodicity by applying Fourier features to a multilayered perceptron network. Our novel algorithm finds a set of Fourier feature frequencies based on the discrete cosine transformation (DCT) of motion. During training, we incrementally added a dominant frequency of the DCT to a current set of Fourier feature frequencies until a given quality threshold was satisfied. We conducted an experiment using CMU motion dataset, and the results suggest that our method achieves overall high compression ratio while maintaining its quality.
Description

CCS Concepts: Computing methodologies --> Animation; Neural networks

        
@inproceedings{
10.2312:egs.20221033
, booktitle = {
Eurographics 2022 - Short Papers
}, editor = {
Pelechano, Nuria
 and
Vanderhaeghe, David
}, title = {{
Neural Motion Compression with Frequency-adaptive Fourier Feature Network
}}, author = {
Tojo, Kenji
 and
Chen, Yifei
 and
Umetani, Nobuyuki
}, year = {
2022
}, publisher = {
The Eurographics Association
}, ISSN = {
1017-4656
}, ISBN = {
978-3-03868-169-4
}, DOI = {
10.2312/egs.20221033
} }
Citation