Publications
Detailed Information
Motion In-betweening for Physically Simulated Characters
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Gopinath, Deepak | - |
dc.contributor.author | Joo, Hanbyul | - |
dc.contributor.author | Won, Jungdam | - |
dc.date.accessioned | 2024-05-08T05:35:15Z | - |
dc.date.available | 2024-05-08T05:35:15Z | - |
dc.date.created | 2023-04-12 | - |
dc.date.created | 2023-04-12 | - |
dc.date.issued | 2022-12 | - |
dc.identifier.citation | Proceedings - SIGGRAPH Asia 2022 Posters, p. 3564186 | - |
dc.identifier.uri | https://hdl.handle.net/10371/201171 | - |
dc.description.abstract | © 2022 Owner/Author.We present a motion in-betweening framework to generate high quality, physically plausible character animation when we are given temporally sparse keyframes as soft animation constraints. More specifically, we learn imitation policies for physically simulated characters by using deep reinforcement learning where the policies can access limited information only. Once learned, the physically simulated characters are capable of adapting to external perturbations while following given sparse input keyframes. We demonstrate the performance of our framework on two different motion datasets and also compare our results with the the results generated by a baseline imitation policy. | - |
dc.language | 영어 | - |
dc.publisher | Association for Computing Machinery, Inc | - |
dc.title | Motion In-betweening for Physically Simulated Characters | - |
dc.type | Article | - |
dc.identifier.doi | 10.1145/3550082.3564186 | - |
dc.citation.journaltitle | Proceedings - SIGGRAPH Asia 2022 Posters | - |
dc.identifier.scopusid | 2-s2.0-85145553554 | - |
dc.citation.startpage | 3564186 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Joo, Hanbyul | - |
dc.contributor.affiliatedAuthor | Won, Jungdam | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Character Animation | - |
dc.subject.keywordAuthor | Deep Learning | - |
dc.subject.keywordAuthor | Multi-agent | - |
dc.subject.keywordAuthor | Neural Network | - |
dc.subject.keywordAuthor | Physics-based Simulation and Control | - |
dc.subject.keywordAuthor | Reinforcement Learning | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.