본문

서브메뉴

Enabling Compact, High-Quality Holographic Displays with Artificial Intelligence
Enabling Compact, High-Quality Holographic Displays with Artificial Intelligence
Enabling Compact, High-Quality Holographic Displays with Artificial Intelligence

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104855
ISBN  
9798288815256
DDC  
531.11
저자명  
Gopakumar, Manu.
서명/저자  
Enabling Compact, High-Quality Holographic Displays with Artificial Intelligence
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
188 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
주기사항  
Advisor: Wetzstein, Gordon.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Emerging technologies such as spatial computing systems and artificial intelligence-powered smart glasses provide us with a glimpse into a future where wearable displays transform the way we interact with one another and our computing devices. However, for these systems to achieve widespread adoption, the near-eye displays in these devices must satisfy demanding requirements for perceptual realism and user comfort. This dissertation examines how holographic displays may be uniquely suited to address these challenges by manipulating light as a wave to deliver complete 3D depth cues, correct visual aberrations in the user or downstream optics, enhance light efficiency, and enable more compact device form factors. In this work, I present a series of artificial intelligence--driven computer-generated holography algorithms designed to unlock this potential. First, I discuss how learned wave propagation models can be used to accurately characterize all the phenomena present in holographic display prototypes, enabling higher quality experimental holograms. Next, I present how the synthesis of partially-coherent holograms can reproduce full 3D and 4D visual cues. Finally, I explain how these propagation models can be co-designed with novel waveguide-based holographic near-eye display designs to deliver high-quality 3D holograms in compact wearable systems. Together, these methods demonstrate how emerging deep learning techniques can be used to effectively manage the unprecedented degrees-of-freedom of holographic displays. Moving forward, this use of machine learning-based computation paired with the precise control of holographic displays can fundamentally change how we design display systems and enable a new generation of wearable displays with better perceptual realism and user comfort.
일반주제명  
Inertia
일반주제명  
Augmented reality
일반주제명  
Visualization
일반주제명  
Computer engineering
키워드  
Emerging technologies
키워드  
Computer-generated holography algorithms
키워드  
Near-eye display designs
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359245
■00520260202104855
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288815256
■035    ▼a(MiAaPQ)AAI32201003
■035    ▼a(MiAaPQ)Stanfordvd005qj7115
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a531.11
■1001  ▼aGopakumar,  Manu.
■24510▼aEnabling  Compact,  High-Quality  Holographic  Displays  with  Artificial  Intelligence
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a188  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-02,  Section:  B.
■500    ▼aAdvisor:  Wetzstein,  Gordon.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aEmerging  technologies  such  as  spatial  computing  systems  and  artificial  intelligence-powered  smart  glasses  provide  us  with  a  glimpse  into  a  future  where  wearable  displays  transform  the  way  we  interact  with  one  another  and  our  computing  devices.  However,  for  these  systems  to  achieve  widespread  adoption,  the  near-eye  displays  in  these  devices  must  satisfy  demanding  requirements  for  perceptual  realism  and  user  comfort.  This  dissertation  examines  how  holographic  displays  may  be  uniquely  suited  to  address  these  challenges  by  manipulating  light  as  a  wave  to  deliver  complete  3D  depth  cues,  correct  visual  aberrations  in  the  user  or  downstream  optics,  enhance  light  efficiency,  and  enable  more  compact  device  form  factors.  In  this  work,  I  present  a  series  of  artificial  intelligence--driven  computer-generated  holography  algorithms  designed  to  unlock  this  potential.  First,  I  discuss  how  learned  wave  propagation  models  can  be  used  to  accurately  characterize  all  the  phenomena  present  in  holographic  display  prototypes,  enabling  higher  quality  experimental  holograms.  Next,  I  present  how  the  synthesis  of  partially-coherent  holograms  can  reproduce  full  3D  and  4D  visual  cues.  Finally,  I  explain  how  these  propagation  models  can  be  co-designed  with  novel  waveguide-based  holographic  near-eye  display  designs  to  deliver  high-quality  3D  holograms  in  compact  wearable  systems.  Together,  these  methods  demonstrate  how  emerging  deep  learning  techniques  can  be  used  to  effectively  manage  the  unprecedented  degrees-of-freedom  of  holographic  displays.  Moving  forward,  this  use  of  machine  learning-based  computation  paired  with  the  precise  control  of  holographic  displays  can  fundamentally  change  how  we  design  display  systems  and  enable  a  new  generation  of  wearable  displays  with  better  perceptual  realism  and  user  comfort.
■590    ▼aSchool  code:  0212.
■650  4▼aInertia
■650  4▼aAugmented  reality
■650  4▼aVisualization
■650  4▼aComputer  engineering
■653    ▼aEmerging  technologies
■653    ▼aComputer-generated  holography  algorithms
■653    ▼aNear-eye  display  designs
■690    ▼a0800
■690    ▼a0464
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-02B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359245▼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

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF14916 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.