서브메뉴
검색
Generative Reconstruction of Human Motion
Generative Reconstruction of Human Motion
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105613
- ISBN
- 9798265429438
- DDC
- 006.3
- 저자명
- Li, Jiaman.
- 서명/저자
- Generative Reconstruction of Human Motion
- 발행사항
- [Sl] : Stanford University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 111 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
- 주기사항
- Advisor: Liu, Karen;Wu, Jiajun.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2025.
- 초록/해제
- 요약Human movement is inherently complex and diverse, grounded in interaction with the physical world-ranging from everyday actions like walking or cooking to skilled motions such as dance or gymnastics. These motions are essential for enabling embodied agents, whether virtual avatars or physical robots, to move purposefully and interact effectively. In virtual environments, human motion drives realistic character behavior, supports robot policy training in simulation, and powers lifelike avatars in mixed-reality applications. In the physical world, humanoid robots can benefit from human motion data to learn agile motor skills-like dancing-and accomplish functional tasks such as preparing coffee or performing household chores. While motion capture provides the most accurate way to obtain human motion data, it requires specialized hardware, controlled environments, and time-consuming setup, which limits scalability and diversity. As a result, capturing the breadth of human activities found in everyday life remains difficult. To overcome these limitations, we can turn to more accessible sources-data that are easier to capture or already widely available, such as third-person videos, egocentric recordings, or object-centric signals from a single sensor. These modalities offer the potential to recover diverse human motions across a broad range of real-world scenarios, but they are inherently sparse and under-constrained.In this dissertation, I address the challenge of reconstructing human motion from such sparse and under-constrained observations by framing the problem within a generative modeling paradigm. I develop a series of generative approaches that leverage learned motion priors to reconstruct 3D human motion from 2D video or other minimal inputs. First, I introduce a framework that leverages 2D motion priors learned from monocular video to reconstruct generalized 3D motion. Second, I show how egocentric video can be used to infer full-body motion grounded in 3D environments. Third, I present a method for reconstructing human motion from dynamic object trajectories. Finally, I extend this formulation to handle even sparser input by generating human and object motion from abstract control signals such as language. Together, these contributions enable scalable and data-efficient acquisition of human motion from accessible observations, broaden the diversity of motions that can be generated, and move us closer to creating intelligent agents that act and interact naturally in the physical world.
- 일반주제명
- Diffusion models
- 일반주제명
- Geometry
- 일반주제명
- Robotics
- 키워드
- Gymnastics
- 키워드
- Physical robots
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 87-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017360746
■00520260202105613
■006m o d
■007cr#unu||||||||
■020 ▼a9798265429438
■035 ▼a(MiAaPQ)AAI32316429
■035 ▼a(MiAaPQ)Stanfordsp112tf7344
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a006.3
■1001 ▼aLi, Jiaman.
■24510▼aGenerative Reconstruction of Human Motion
■260 ▼a[Sl]▼bStanford University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a111 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-06, Section: B.
■500 ▼aAdvisor: Liu, Karen;Wu, Jiajun.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2025.
■520 ▼aHuman movement is inherently complex and diverse, grounded in interaction with the physical world-ranging from everyday actions like walking or cooking to skilled motions such as dance or gymnastics. These motions are essential for enabling embodied agents, whether virtual avatars or physical robots, to move purposefully and interact effectively. In virtual environments, human motion drives realistic character behavior, supports robot policy training in simulation, and powers lifelike avatars in mixed-reality applications. In the physical world, humanoid robots can benefit from human motion data to learn agile motor skills-like dancing-and accomplish functional tasks such as preparing coffee or performing household chores. While motion capture provides the most accurate way to obtain human motion data, it requires specialized hardware, controlled environments, and time-consuming setup, which limits scalability and diversity. As a result, capturing the breadth of human activities found in everyday life remains difficult. To overcome these limitations, we can turn to more accessible sources-data that are easier to capture or already widely available, such as third-person videos, egocentric recordings, or object-centric signals from a single sensor. These modalities offer the potential to recover diverse human motions across a broad range of real-world scenarios, but they are inherently sparse and under-constrained.In this dissertation, I address the challenge of reconstructing human motion from such sparse and under-constrained observations by framing the problem within a generative modeling paradigm. I develop a series of generative approaches that leverage learned motion priors to reconstruct 3D human motion from 2D video or other minimal inputs. First, I introduce a framework that leverages 2D motion priors learned from monocular video to reconstruct generalized 3D motion. Second, I show how egocentric video can be used to infer full-body motion grounded in 3D environments. Third, I present a method for reconstructing human motion from dynamic object trajectories. Finally, I extend this formulation to handle even sparser input by generating human and object motion from abstract control signals such as language. Together, these contributions enable scalable and data-efficient acquisition of human motion from accessible observations, broaden the diversity of motions that can be generated, and move us closer to creating intelligent agents that act and interact naturally in the physical world.
■590 ▼aSchool code: 0212.
■650 4▼aDiffusion models
■650 4▼aGeometry
■650 4▼aRobotics
■653 ▼aGymnastics
■653 ▼aPhysical robots
■690 ▼a0771
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g87-06B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360746▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
detalle info
- Reserva
- No existe
- Mi carpeta
- Primera solicitud
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


