서브메뉴
검색
Combining Neural Networks and Physics-Based Simulation for Cloth and Flesh Dynamics
Combining Neural Networks and Physics-Based Simulation for Cloth and Flesh Dynamics
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152943
- ISBN
- 9798342138611
- DDC
- 646
- 저자명
- Jin, Yongxu.
- 서명/저자
- Combining Neural Networks and Physics-Based Simulation for Cloth and Flesh Dynamics
- 발행사항
- [Sl] : Stanford University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 85 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
- 주기사항
- Advisor: Fedkiw, Ron.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2024.
- 초록/해제
- 요약Physics-based simulation techniques have long been established for various offline applications, yet real-time dynamic simulation remains a formidable challenge. Despite advancements in modern game engines like Unreal Engine 5, achieving high-resolution, real-time simulation capabilities remains limited. Recently, researchers have shown interest in using neural networks to approximate dynamic simulation, thanks to their fast inference on GPUs. However, although effective at approximating kinematics or quasistatic simulation, purely data-driven approaches often struggle with dynamic simulations (involving velocity and momentum information) due to potential overfitting and poor generalization with time series data. This limitation makes them unsuitable for real-world applications. Other efforts have tried using neural networks to upsample real-time, low-resolution simulations, but achieving good low-resolution results with conventional methods is very challenging.This thesis aims to pioneer a paradigm for real-time, high-fidelity physics simulation, with a focus on practical implementation within current game engines. Motivated by recent advancements in neural networks for capturing quasistatic simulations (referred to as quasistatic neural networks, or QNNs), we propose to rethink the need for dynamic components given QNN-based enhancements and redesign real-time physics models to primarily capture the ballistic motion of full dynamics, which can then be enhanced by QNNs to obtain the full shape. These meticulously designed physics models ensure stability, robustness, and performance that surpass real-time requirements. Concurrently, the lightweight QNNs can capture quasistatic shapes, facilitating ease of training and robust generalization. This thesis comprises two primary papers: one addressing human flesh simulation and the other focusing on the simulation of loose-fitting clothing.
- 일반주제명
- Clothing
- 일반주제명
- Computer & video games
- 일반주제명
- Physics
- 일반주제명
- Success
- 일반주제명
- Neural networks
- 일반주제명
- Bones
- 일반주제명
- Computer science
- 일반주제명
- Mathematics
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 86-04B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164285
■00520250211152943
■006m o d
■007cr#unu||||||||
■020 ▼a9798342138611
■035 ▼a(MiAaPQ)AAI31591783
■035 ▼a(MiAaPQ)Stanfordmf757zb2546
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a646
■1001 ▼aJin, Yongxu.
■24510▼aCombining Neural Networks and Physics-Based Simulation for Cloth and Flesh Dynamics
■260 ▼a[Sl]▼bStanford University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a85 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-04, Section: B.
■500 ▼aAdvisor: Fedkiw, Ron.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2024.
■520 ▼aPhysics-based simulation techniques have long been established for various offline applications, yet real-time dynamic simulation remains a formidable challenge. Despite advancements in modern game engines like Unreal Engine 5, achieving high-resolution, real-time simulation capabilities remains limited. Recently, researchers have shown interest in using neural networks to approximate dynamic simulation, thanks to their fast inference on GPUs. However, although effective at approximating kinematics or quasistatic simulation, purely data-driven approaches often struggle with dynamic simulations (involving velocity and momentum information) due to potential overfitting and poor generalization with time series data. This limitation makes them unsuitable for real-world applications. Other efforts have tried using neural networks to upsample real-time, low-resolution simulations, but achieving good low-resolution results with conventional methods is very challenging.This thesis aims to pioneer a paradigm for real-time, high-fidelity physics simulation, with a focus on practical implementation within current game engines. Motivated by recent advancements in neural networks for capturing quasistatic simulations (referred to as quasistatic neural networks, or QNNs), we propose to rethink the need for dynamic components given QNN-based enhancements and redesign real-time physics models to primarily capture the ballistic motion of full dynamics, which can then be enhanced by QNNs to obtain the full shape. These meticulously designed physics models ensure stability, robustness, and performance that surpass real-time requirements. Concurrently, the lightweight QNNs can capture quasistatic shapes, facilitating ease of training and robust generalization. This thesis comprises two primary papers: one addressing human flesh simulation and the other focusing on the simulation of loose-fitting clothing.
■590 ▼aSchool code: 0212.
■650 4▼aClothing
■650 4▼aComputer & video games
■650 4▼aPhysics
■650 4▼aSuccess
■650 4▼aOrdinary differential equations
■650 4▼aNeural networks
■650 4▼aBones
■650 4▼aComputer science
■650 4▼aMathematics
■690 ▼a0605
■690 ▼a0800
■690 ▼a0984
■690 ▼a0405
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g86-04B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164285▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Buch Status
- Reservierung
- frei buchen
- Meine Mappe
- Erste Aufräumarbeiten Anfrage
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


