본문

서브메뉴

Combining Neural Networks and Physics-Based Simulation for Cloth and Flesh Dynamics
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  
Ordinary differential equations
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


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Buch Status

    • Reservierung
    • frei buchen
    • Meine Mappe
    • Erste Aufräumarbeiten Anfrage
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Sammlungen
    Registrierungsnummer callnumber Standort Verkehr Status Verkehr Info
    TF10561 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Kredite nur für Ihre Daten gebucht werden. Wenn Sie buchen möchten Reservierungen, klicken Sie auf den Button.

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.