본문

서브메뉴

Reconstructing 3D Geometries for Scientific Applications: An Image to Simulation Pipeline
Reconstructing 3D Geometries for Scientific Applications: An Image to Simulation Pipeline
Reconstructing 3D Geometries for Scientific Applications: An Image to Simulation Pipeline

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211151410
ISBN  
9798384450290
DDC  
004
저자명  
Ramirez de Chanlatte, Marissa Isabella.
서명/저자  
Reconstructing 3D Geometries for Scientific Applications: An Image to Simulation Pipeline
발행사항  
[Sl] : University of California, Berkeley, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
95 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
주기사항  
Advisor: Colella, Phillip;Darrell, Trevor.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2024.
초록/해제  
요약Numerical simulation is a powerful tool that aids scientists in the understanding of the physics of the world around them, but to achieve an understanding of the physics, we must start with a representation of the geometry. Embedded Boundary (EB) simulation provides robust, automatic handling of complex geometries, enabling large scale physics simulations, but it still depends on an initial 3D implicit function representation of said geometry. These geometries are typically user-supplied through 3D design specifications, but for many domains of interest (i.e. outdoor scenes such as cities or forests) no such design specifications exist. This means that simulations of this nature rely on expensive, time consuming, and often noisy measurements from LiDAR or other sources, and because of the cost and lack of quality in the results, there have been relatively few 3D, large scale EB simulations of outdoor scenes. Recent advances in computer vision, such as Neural Radiance Fields (NeRFs) and their corresponding Neural Signed Distance Functions (NeuS) have made producing 3D implicit functions from images much easier, but they have not yet been studied from the view point of numerical simulation. In this thesis, we present for the first time a 3D simulation using the Embedded Boundary method on a neural-SDF learned from images, demonstrating the feasibility of this approach. In the process, we identify several challenges in bridging the two methods, including differences in how the computer vision community measures error/uncertainty and what types of error/uncertainty actually matter in an EB simulation, and present appropriate alternatives. In the following chapters, we describe several methods for learning 3D geometries from RGB images, discuss their suitability for scientific tasks, and do an in-depth analysis of their error and uncertainty and how those affect a physics simulation. We finally discuss this pipeline through the lens of a high-impact, real-world application: forest management. We reconstruct a forest scene using NeRF that is visibly much more appropriate for simulation than previous examples. We also discuss what challenges this real-world data presents and how the technology presented in this thesis can be used to answer real scientific questions.
일반주제명  
Computer science
일반주제명  
Applied mathematics
일반주제명  
Fluid mechanics
키워드  
3D reconstruction models
키워드  
Computational fluid dynamics
키워드  
Computer vision
키워드  
Uncertainty quantification
기타저자  
University of California, Berkeley Applied Science & Technology
기본자료저록  
Dissertations Abstracts International. 86-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161542
■00520250211151410
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384450290
■035    ▼a(MiAaPQ)AAI31292649
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aRamirez  de  Chanlatte,  Marissa  Isabella.
■24510▼aReconstructing  3D  Geometries  for  Scientific  Applications:  An  Image  to  Simulation  Pipeline
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a95  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  B.
■500    ▼aAdvisor:  Colella,  Phillip;Darrell,  Trevor.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2024.
■520    ▼aNumerical  simulation  is  a  powerful  tool  that  aids  scientists  in  the  understanding  of  the  physics  of  the  world  around  them,  but  to  achieve  an  understanding  of  the  physics,  we  must  start  with  a  representation  of  the  geometry.  Embedded  Boundary  (EB)  simulation  provides  robust,  automatic  handling  of  complex  geometries,  enabling  large  scale  physics  simulations,  but  it  still  depends  on  an  initial  3D  implicit  function  representation  of  said  geometry.  These  geometries  are  typically  user-supplied  through  3D  design  specifications,  but  for  many  domains  of  interest  (i.e.  outdoor  scenes  such  as  cities  or  forests)  no  such  design  specifications  exist.  This  means  that  simulations  of  this  nature  rely  on  expensive,  time  consuming,  and  often  noisy  measurements  from  LiDAR  or  other  sources,  and  because  of  the  cost  and  lack  of  quality  in  the  results,  there  have  been  relatively  few  3D,  large  scale  EB  simulations  of  outdoor  scenes.  Recent  advances  in  computer  vision,  such  as  Neural  Radiance  Fields  (NeRFs)  and  their  corresponding  Neural  Signed  Distance  Functions  (NeuS)  have  made  producing  3D  implicit  functions  from  images  much  easier,  but  they  have  not  yet  been  studied  from  the  view  point  of  numerical  simulation.  In  this  thesis,  we  present  for  the  first  time  a  3D  simulation  using  the  Embedded  Boundary  method  on  a  neural-SDF  learned  from  images,  demonstrating  the  feasibility  of  this  approach.  In  the  process,  we  identify  several  challenges  in  bridging  the  two  methods,  including  differences  in  how  the  computer  vision  community  measures  error/uncertainty  and  what  types  of  error/uncertainty  actually  matter  in  an  EB  simulation,  and  present  appropriate  alternatives.  In  the  following  chapters,  we  describe  several  methods  for  learning  3D  geometries  from  RGB  images,  discuss  their  suitability  for  scientific  tasks,  and  do  an  in-depth  analysis  of  their  error  and  uncertainty  and  how  those  affect  a  physics  simulation.  We  finally  discuss  this  pipeline  through  the  lens  of  a  high-impact,  real-world  application:  forest  management.  We  reconstruct  a  forest  scene  using  NeRF  that  is  visibly  much  more  appropriate  for  simulation  than  previous  examples.  We  also  discuss  what  challenges  this  real-world  data  presents  and  how  the  technology  presented  in  this  thesis  can  be  used  to  answer  real  scientific  questions.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science
■650  4▼aApplied  mathematics
■650  4▼aFluid  mechanics
■653    ▼a3D  reconstruction  models
■653    ▼aComputational  fluid  dynamics
■653    ▼aComputer  vision
■653    ▼aUncertainty  quantification
■690    ▼a0984
■690    ▼a0364
■690    ▼a0204
■71020▼aUniversity  of  California,  Berkeley▼bApplied  Science  &  Technology.
■7730  ▼tDissertations  Abstracts  International▼g86-04B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161542▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF09930 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.