Home » Single publication

Temporal Parameter-free Deep Skinning of Animated Meshes

Anastasia Moutafidou, Vasileios Toulatzis and Ioannis Fudos
CGI 2021, LNCS Proceedings, pp 3-24

Visualization of error versus previous methods

Abstract

In computer graphics, animation compression is essential for efficient storage, streaming and reproduction of animated meshes. Previous work has presented efficient techniques for compression by deriving skinning transformations and weights using clustering of vertices based on geometric features of vertices over time. In this work we present a novel approach that assigns vertices to bone-influenced clusters and derives weights using deep learning through a training set that consists of pairs of vertex trajectories (temporal vertex sequences) and the corresponding weights drawn from fully rigged animated characters. The approximation error of the resulting linear blend skinning scheme is significantly lower than the error of competent previous methods by producing at the same time a minimal number of bones. Furthermore, the optimal set of transformation and vertices is derived in fewer iterations due to the better initial positioning in the multidimensional variable space. Our method requires no parameters to be determined or tuned by the user during the entire process of compressing a mesh animation sequence.
View bibtex
Download video
View paper
Source code
Presentation
Link
@inproceedings{DBLP:conf/cgi/MoutafidouTF21,
author = {Anastasia Moutafidou and
Vasileios Toulatzis and
Ioannis Fudos},
editor = {Nadia Magnenat{-}Thalmann and
Victoria Interrante and
Daniel Thalmann and
George Papagiannakis and
Bin Sheng and
Jinman Kim and
Marina L. Gavrilova},
title = {Temporal Parameter-Free Deep Skinning of Animated Meshes},
booktitle = {Advances in Computer Graphics - 38th Computer Graphics International
Conference, {CGI} 2021, Virtual Event, September 6-10, 2021, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {13002},
pages = {3--24},
publisher = {Springer},
year = {2021},
url = {https://doi.org/10.1007/978-3-030-89029-2\_1},
doi = {10.1007/978-3-030-89029-2\_1}
}

close

Go back to Publications