Detailed Information

SAME: Skeleton-Agnostic Motion Embedding for Character Animation

Cited 0 time in Web of Science Cited 0 time in Scopus

Lee, Sunmin; Kang, Taeho; Park, Jungnam; Lee, Jehee; Won, Jungdam

Issue Date
Association for Computing Machinery, Inc
Proceedings - SIGGRAPH Asia 2023 Conference Papers, SA 2023
Learning deep neural networks on human motion data has become common in computer graphics research, but the heterogeneity of available datasets poses challenges for training large-scale networks. This paper presents a framework that allows us to solve various animation tasks in a skeleton-agnostic manner. The core of our framework is to learn an embedding space to disentangle skeleton-related information from input motion while preserving semantics, which we call Skeleton-Agnostic Motion Embedding (SAME). To efficiently learn the embedding space, we develop a novel autoencoder with graph convolution networks and provide new formulations of various animation tasks operating in the SAME space. We showcase various examples, including retargeting, reconstruction, and interactive character control, and conduct an ablation study to validate design choices made during development.
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • College of Engineering
  • Dept. of Computer Science and Engineering
Research Area Cryptography, Privacy, Security


Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.