DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이성희 | - |
dc.contributor.author | Jin, Yurhee | - |
dc.contributor.author | 진유리 | - |
dc.date.accessioned | 2024-07-30T19:30:49Z | - |
dc.date.available | 2024-07-30T19:30:49Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096193&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321408 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 문화기술대학원, 2024.2,[iii, 16 p. :] | - |
dc.description.abstract | We present CMNet, aimed at synthesizing human motions interacting with diverse sittable objects. Leveraging the MoGlow[1] architecture, our approach involves two distinct models - the Contact Generator and the Full-body Pose Generator. The former generates plausible contact positions for selected joints which correlates with chairs, while the latter synthesizes full-body motions based on these contacts, facilitated through a cascaded approach. Utilizing control signals derived from interaction between human motion and chair, our method ensures the synthesis of realistic and diverse human motions within various environmental settings. Experimental validation on the sorted CHAIRS dataset[2] demonstrates the efficacy of CMNet in generating diverse and realistic human interaction motions with chairs. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 모션 생성▼a인간 객체 상호작용▼a생성 모델▼a데이터 기반 학습▼a머신 러닝 | - |
dc.subject | Motion synthesis▼aHuman-object interaction▼aGenerative model▼aData-driven learning▼aMachine learning | - |
dc.title | CMNet : Cascading Moglow models for environment-aware motion synthesis | - |
dc.title.alternative | 환경 인식 모션 합성을 위한 계단식 모글로우 모델 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :문화기술대학원, | - |
dc.contributor.alternativeauthor | Lee, Sung-Hee | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.