File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3450626.3459881
- Scopus: eid_2-s2.0-85111254885
- WOS: WOS:000674930900058
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Neural animation layering for synthesizing martial arts movements
Title | Neural animation layering for synthesizing martial arts movements |
---|---|
Authors | |
Keywords | character animation character control character interactions deep learning human motion |
Issue Date | 2021 |
Publisher | Association for Computing Machinery, Inc. The Journal's web site is located at http://tog.acm.org |
Citation | ACM Transactions on Graphics, 2021, v. 40 n. 4, p. article no. 92 How to Cite? |
Abstract | Interactively synthesizing novel combinations and variations of character movements from different motion skills is a key problem in computer animation. In this paper, we propose a deep learning framework to produce a large variety of martial arts movements in a controllable manner from raw motion capture data. Our method imitates animation layering using neural networks with the aim to overcome typical challenges when mixing, blending and editing movements from unaligned motion sources. The framework can synthesize novel movements from given reference motions and simple user controls, and generate unseen sequences of locomotion, punching, kicking, avoiding and combinations thereof, but also reconstruct signature motions of different fighters, as well as close-character interactions such as clinching and carrying by learning the spatial joint relationships. To achieve this goal, we adopt a modular framework which is composed of the motion generator and a set of different control modules. The motion generator functions as a motion manifold that projects novel mixed/edited trajectories to natural full-body motions, and synthesizes realistic transitions between different motions. The control modules are task dependent and can be developed and trained separately by engineers to include novel motion tasks, which greatly reduces network iteration time when working with large-scale datasets. Our modular framework provides a transparent control interface for animators that allows modifying or combining movements after network training, and enables iterative adding of control modules for different motion tasks and behaviors. Our system can be used for offline and online motion generation alike, and is relevant for real-time applications such as computer games. |
Persistent Identifier | http://hdl.handle.net/10722/304081 |
ISSN | 2023 Impact Factor: 7.8 2023 SCImago Journal Rankings: 7.766 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Starke, S | - |
dc.contributor.author | Zhao, Y | - |
dc.contributor.author | Zinno, F | - |
dc.contributor.author | Komura, T | - |
dc.date.accessioned | 2021-09-23T08:54:58Z | - |
dc.date.available | 2021-09-23T08:54:58Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | ACM Transactions on Graphics, 2021, v. 40 n. 4, p. article no. 92 | - |
dc.identifier.issn | 0730-0301 | - |
dc.identifier.uri | http://hdl.handle.net/10722/304081 | - |
dc.description.abstract | Interactively synthesizing novel combinations and variations of character movements from different motion skills is a key problem in computer animation. In this paper, we propose a deep learning framework to produce a large variety of martial arts movements in a controllable manner from raw motion capture data. Our method imitates animation layering using neural networks with the aim to overcome typical challenges when mixing, blending and editing movements from unaligned motion sources. The framework can synthesize novel movements from given reference motions and simple user controls, and generate unseen sequences of locomotion, punching, kicking, avoiding and combinations thereof, but also reconstruct signature motions of different fighters, as well as close-character interactions such as clinching and carrying by learning the spatial joint relationships. To achieve this goal, we adopt a modular framework which is composed of the motion generator and a set of different control modules. The motion generator functions as a motion manifold that projects novel mixed/edited trajectories to natural full-body motions, and synthesizes realistic transitions between different motions. The control modules are task dependent and can be developed and trained separately by engineers to include novel motion tasks, which greatly reduces network iteration time when working with large-scale datasets. Our modular framework provides a transparent control interface for animators that allows modifying or combining movements after network training, and enables iterative adding of control modules for different motion tasks and behaviors. Our system can be used for offline and online motion generation alike, and is relevant for real-time applications such as computer games. | - |
dc.language | eng | - |
dc.publisher | Association for Computing Machinery, Inc. The Journal's web site is located at http://tog.acm.org | - |
dc.relation.ispartof | ACM Transactions on Graphics | - |
dc.rights | ACM Transactions on Graphics. Copyright © Association for Computing Machinery, Inc. | - |
dc.rights | ©ACM, YYYY. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in PUBLICATION, {VOL#, ISS#, (DATE)} http://doi.acm.org/10.1145/nnnnnn.nnnnnn | - |
dc.subject | character animation | - |
dc.subject | character control | - |
dc.subject | character interactions | - |
dc.subject | deep learning | - |
dc.subject | human motion | - |
dc.title | Neural animation layering for synthesizing martial arts movements | - |
dc.type | Article | - |
dc.identifier.email | Komura, T: taku@cs.hku.hk | - |
dc.identifier.authority | Komura, T=rp02741 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3450626.3459881 | - |
dc.identifier.scopus | eid_2-s2.0-85111254885 | - |
dc.identifier.hkuros | 325508 | - |
dc.identifier.volume | 40 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | article no. 92 | - |
dc.identifier.epage | article no. 92 | - |
dc.identifier.isi | WOS:000674930900058 | - |
dc.publisher.place | United States | - |