A variational U‐Net for motion retargeting

Motion retargeting is the process of copying motion from one character (source) to another (target) when the source and target body sizes and proportions (of arms, legs, torso, etc.) are different. The problem of automatic motion retargeting has been studied for several decades; however, the motion...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer animation and virtual worlds Ročník 31; číslo 4-5
Hlavní autoři: Uk Kim, Seong, Jang, Hanyoung, Kim, Jongmin
Médium: Journal Article
Jazyk:angličtina
Vydáno: Chichester Wiley Subscription Services, Inc 01.07.2020
Témata:
Body parts
Computer architecture
Copying
deep learning
Human motion
motion retargeting
Neural networks
Optimization
Torso
ISSN:1546-4261, 1546-427X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Motion retargeting is the process of copying motion from one character (source) to another (target) when the source and target body sizes and proportions (of arms, legs, torso, etc.) are different. The problem of automatic motion retargeting has been studied for several decades; however, the motion quality obtained with the application of current approaches is on occasion unrealistic. This is because previous methods, which are mainly based on numerical optimization, generally do not incorporate prior knowledge of the details and nuances of human movements. To address these issues, we present a novel human motion retargeting system using a deep learning framework with large‐scale motion data to produce high‐quality retargeted human motion. We establish a deep‐learning‐based motion retargeting system using a variational deep autoencoder combining the deep convolutional inverse graphics network (DC‐IGN) and the U‐Net. The DC‐IGN is utilized for disentangling the motion of each body part, while the U‐Net is employed to preserve details of the original motion. We conduct several experiments to validate the proposed motion retargeting system, and find that ours achieves better accuracy along with reduced computational burden when compared with the conventional motion retargeting approach and other neural network architectures. We design a novel motion retargeting system by using the deep autoencoder combining the Deep Convolution Inverse Graphics Network (DC‐IGN) and the U‐Net to produce high‐quality human motion. The retargeted motion is fully‐automatically and naturally generated from the given input motion and bone length ratios. To validate the proposed motion retargeting system, we conduct several experiments and achieve more accuracy and less computational burden when compared with the conventional motion retargeting approach and other neural network architectures.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1546-4261
1546-427X
DOI:10.1002/cav.1947