본문

서브메뉴

상세정보

Data-Driven Design of High-Dimensional, Snapshot Computational Imaging Systems.
Data-Driven Design of High-Dimensional, Snapshot Computational Imaging Systems.
Data-Driven Design of High-Dimensional, Snapshot Computational Imaging Systems.

상세정보

자료유형  
 학위논문(국외)
기본표목-개인명  
표제와 책임표시사항  
Data-Driven Design of High-Dimensional, Snapshot Computational Imaging Systems.
발행, 배포, 간사 사항  
발행, 배포, 간사 사항  
Ann Arbor : ProQuest Dissertations & Theses , 2025
    형태사항  
    128 p.
    일반주기  
    Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
    일반주기  
    Advisor: Waller, Laura.
    학위논문주기  
    Thesis (Ph.D.)--University of California, Berkeley, 2025.
    요약 등 주기  
    요약Modern imaging systems increasingly rely on computational methods to extract high-dimensional information from 2D optical measurements. Examples include snapshot 3D microscopy systems that capture volumetric data in a single exposure and hyperspectral imagers that simultaneously measure spatial and spectral information across dozens of wavelength channels. Designing such systems is challenging because it requires jointly optimizing both the optical hardware that encodes the scene and the computational algorithms that decode the measurements, a process complicated by the non-convex, high-dimensional parameter spaces and computationally expensive end-to-end training requirements. In this dissertation, we present data-driven approaches that address these challenges through physics-based simulation and information-theoretic design principles. We first develop a memory-efficient, end-to-end pipeline that jointly optimizes optical elements and neural reconstruction algorithms using differentiable simulation, demonstrating this method on a snapshot 3D fluorescence microscope that achieves improved resolution over heuristic designs. We then present a compact snapshot hyperspectral fluorescence microscope with a custom iterative reconstruction algorithm tailored to its physical model.To overcome the computational limitations of end-to-end optimization and accommodate non-differentiable reconstruction algorithms, we develop an information-theoretic optimization framework that treats optical design as a mutual information maximization problem. This approach, implemented through the IDEAL and IDEAL-IO methods, decouples encoder design from specific reconstruction implementations. By directly maximizing the information content of measurements rather than optimizing reconstruction fidelity, this framework provides a generalizable design principle that transcends particular decoder architectures while reducing the computational requirements in comparison to end-to-end design.The methods developed in this dissertation demonstrate that principled, simulation-driven design can achieve improved performance across diverse high-dimensional imaging modalities while maintaining computational tractability.
    주제명부출표목-일반주제명  
    주제명부출표목-일반주제명  
    주제명부출표목-일반주제명  
    주제명부출표목-일반주제명  
    비통제 색인어  
    비통제 색인어  
    비통제 색인어  
    비통제 색인어  
    비통제 색인어  
    부출표목-단체명  
    기본자료저록  
    Dissertations Abstracts International. 87-04B.
    전자적 위치 및 접속  
     원문정보보기

    MARC

     008260219s2025        us  ||||||||||||||c||eng  d
    ■001000017359369
    ■00520260202105109
    ■006m          o    d                
    ■007cr#unu||||||||
    ■020    ▼a9798297601178
    ■035    ▼a(MiAaPQ)AAI32236909
    ■040    ▼aMiAaPQ▼cMiAaPQ
    ■0820  ▼a535
    ■1001  ▼aMarkley,  Eric.
    ■24510▼aData-Driven  Design  of  High-Dimensional,  Snapshot  Computational  Imaging  Systems.
    ■260    ▼a[S.l.]▼bUniversity  of  California,  Berkeley.  ▼c2025
    ■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
    ■300    ▼a128  p.
    ■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-04,  Section:  B.
    ■500    ▼aAdvisor:  Waller,  Laura.
    ■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
    ■520    ▼aModern  imaging  systems  increasingly  rely  on  computational  methods  to  extract  high-dimensional  information  from  2D  optical  measurements.  Examples  include  snapshot  3D  microscopy  systems  that  capture  volumetric  data  in  a  single  exposure  and  hyperspectral  imagers  that  simultaneously  measure  spatial  and  spectral  information  across  dozens  of  wavelength  channels.  Designing  such  systems  is  challenging  because  it  requires  jointly  optimizing  both  the  optical  hardware  that  encodes  the  scene  and  the  computational  algorithms  that  decode  the  measurements,  a  process  complicated  by  the  non-convex,  high-dimensional  parameter  spaces  and  computationally  expensive  end-to-end  training  requirements.  In  this  dissertation,  we  present  data-driven  approaches  that  address  these  challenges  through  physics-based  simulation  and  information-theoretic  design  principles.  We  first  develop  a  memory-efficient,  end-to-end  pipeline  that  jointly  optimizes  optical  elements  and  neural  reconstruction  algorithms  using  differentiable  simulation,  demonstrating  this  method  on  a  snapshot  3D  fluorescence  microscope  that  achieves  improved  resolution  over  heuristic  designs.  We  then  present  a  compact  snapshot  hyperspectral  fluorescence  microscope  with  a  custom  iterative  reconstruction  algorithm  tailored  to  its  physical  model.To  overcome  the  computational  limitations  of  end-to-end  optimization  and  accommodate  non-differentiable  reconstruction  algorithms,  we  develop  an  information-theoretic  optimization  framework  that  treats  optical  design  as  a  mutual  information  maximization  problem.  This  approach,  implemented  through  the  IDEAL  and  IDEAL-IO  methods,  decouples  encoder  design  from  specific  reconstruction  implementations.  By  directly  maximizing  the  information  content  of  measurements  rather  than  optimizing  reconstruction  fidelity,  this  framework  provides  a  generalizable  design  principle  that  transcends  particular  decoder  architectures  while  reducing  the  computational  requirements  in  comparison  to  end-to-end  design.The  methods  developed  in  this  dissertation  demonstrate  that  principled,  simulation-driven  design  can  achieve  improved  performance  across  diverse  high-dimensional  imaging  modalities  while  maintaining  computational  tractability.
    ■590    ▼aSchool  code:  0028.
    ■650  4▼aOptics.
    ■650  4▼aComputer  science.
    ■650  4▼aBioinformatics.
    ■650  4▼aMedical  imaging.
    ■653    ▼aData-driven  design
    ■653    ▼aEnd-to-end  design
    ■653    ▼aInformation  theory
    ■653    ▼aOptimization
    ■653    ▼a3D  fluorescence  microscope
    ■690    ▼a0752
    ■690    ▼a0984
    ■690    ▼a0574
    ■690    ▼a0715
    ■71020▼aUniversity  of  California,  Berkeley▼bBioengineering.
    ■7730  ▼tDissertations  Abstracts  International▼g87-04B.
    ■790    ▼a0028
    ■791    ▼aPh.D.
    ■792    ▼a2025
    ■793    ▼aEnglish
    ■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359369▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

    미리보기

    내보내기

    chatGPT토론

    Ai 추천 관련 도서


      신착도서 더보기
      관련도서 더보기
      최근 3년간 통계입니다.
      SMS 발송 간략정보 이동 상세정보출력

      소장정보

      • 예약
      • 서가에 없는 책 신고
      • 자료배달서비스
      • 나의폴더
      • 우선정리요청
      소장자료
      등록번호 청구기호 소장처 대출가능여부 대출정보
      EM179486 TD   자료대출실(3층) 정리중  정리중 
      마이폴더

      * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

      해당 도서를 다른 이용자가 함께 대출한 도서

      관련도서

      관련 인기도서

      서평쓰기