DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 최성희 | - |
dc.contributor.author | Kim, Beomki | - |
dc.contributor.author | 김범기 | - |
dc.date.accessioned | 2024-07-26T19:31:21Z | - |
dc.date.available | 2024-07-26T19:31:21Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1051098&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321078 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2022.2,[iii, 23 p. :] | - |
dc.description.abstract | Recently, users encounter 3D human motion easily than before according to computer graphics development. Real-time motion generation is often required for interactivity in some motion generation fields such as games. Data-driven generative models for motion demand enough amount of motion clips as a training data set for each type of motion, and it is raised as a problem when the model should generate unusual motions whose motion clips are barely found. Therefore, in this research, we propose a model named Labeled Motion VAEs(L-MVAE). Existing MVAE, or Motion VAEs, uses the latent space of conditional variational autoencoder for reinforcement learning to synthesize desired 3D human motion and can generate motions in real-time. In L-MVAE, label information of motions is added to MVAE with a concept of label distribution. L-MVAE can synthesize motions in real-time likewise, and it produces high-quality motions even with a relatively small size of training data set. The performance of the proposed model is compared with the existing MVAE using the task in which a character moves to a destination. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 실시간 3차원 인체 동작 생성▼a레이블링▼a오토 인코더▼a강화학습 | - |
dc.subject | Real-time 3D human motion generation▼aLabels▼aVariational autoencoder▼aReinforcement learning | - |
dc.title | Real-time 3D human motion generation with labeled motion capture data | - |
dc.title.alternative | 레이블링된 모션 캡처 데이터를 이용한 실시간 3D 인체 동작 생성 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | Choi, Sunghee | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.