본문

서브메뉴

Variational Approaches to 3D Reconstruction from Multiple Depth Images
Variational Approaches to 3D Reconstruction from Multiple Depth Images
Variational Approaches to 3D Reconstruction from Multiple Depth Images

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105509
ISBN  
9798263324889
DDC  
515.35
저자명  
Yang, Huizong.
서명/저자  
Variational Approaches to 3D Reconstruction from Multiple Depth Images
발행사항  
[Sl] : Georgia Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
131 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Yezzi, Anthony J.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2025.
초록/해제  
요약This dissertation introduces a novel variational framework for reconstructing 3D surfaces from depth data acquired by commercial sensors. The work is organized into three main contributions.First, by leveraging variational methods and differential geometry, we derive explicit expressions for occluding boundaries-a key source of non-differentiability in 3D-2D matching tasks. Unlike prior approaches that rely on curvature measures or implicit representations, our work characterizes the local structure of occluding curves directly from the surface geometry. In particular, we demonstrate that the tangent of an occluding curve can be extracted from the surface's second-order structure along the viewing direction, decomposing naturally into components corresponding to geodesic torsion and normal curvature. This result not only clarifies the role of occluding boundaries but also integrates seamlessly into our implicit reconstruction framework.The second contribution addresses the challenges of reconstructing surfaces from raw, noisy, and incomplete depth maps-a common limitation of commercial depth cameras. We propose a variational framework that enforces global data fidelity while incorporating flexible regularization strategies. A key innovation is the separation of foreground and background modeling, which minimizes the influence of erroneous background data. To further mitigate issues from missing measurements, we introduce a novel inpainting technique that works in concert with an area-penalty regularizer. In addition, a new initialization scheme for the implicit function is presented, accelerating convergence and enhancing reconstruction accuracy, particularly for smooth surfaces.Finally, we exploit the ideas from shape analysis, and develop a new regularizer for neural signed distance function (SDF) reconstruction. By directly addressing the instability introduced by the prevalent Eikonal loss, our regularizer not only improves convergence but also preserves finer geometric details compared to existing methods. Rigorous analysis and extensive experiments on public benchmarks validate its superior performance.In summary, this dissertation demonstrates that integrating variational methods and shape analysis can overcome significant data-quality challenges in 3D reconstruction, while also offering new insights that enrich learning-based approaches.
일반주제명  
Partial differential equations
일반주제명  
Deep learning
일반주제명  
Computer vision
일반주제명  
Benchmarks
일반주제명  
Decomposition
일반주제명  
Missing data
일반주제명  
Visualization
일반주제명  
Geometry
일반주제명  
Computer science
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360338
■00520260202105509
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263324889
■035    ▼a(MiAaPQ)AAI32308085
■035    ▼a(MiAaPQ)GeorgiaTech77940
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a515.35
■1001  ▼aYang,  Huizong.
■24510▼aVariational  Approaches  to  3D  Reconstruction  from  Multiple  Depth  Images
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a131  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Yezzi,  Anthony  J.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2025.
■520    ▼aThis  dissertation  introduces  a  novel  variational  framework  for  reconstructing  3D  surfaces  from  depth  data  acquired  by  commercial  sensors.  The  work  is  organized  into  three  main  contributions.First,  by  leveraging  variational  methods  and  differential  geometry,  we  derive  explicit  expressions  for  occluding  boundaries-a  key  source  of  non-differentiability  in  3D-2D  matching  tasks.  Unlike  prior  approaches  that  rely  on  curvature  measures  or  implicit  representations,  our  work  characterizes  the  local  structure  of  occluding  curves  directly  from  the  surface  geometry.  In  particular,  we  demonstrate  that  the  tangent  of  an  occluding  curve  can  be  extracted  from  the  surface's  second-order  structure  along  the  viewing  direction,  decomposing  naturally  into  components  corresponding  to  geodesic  torsion  and  normal  curvature.  This  result  not  only  clarifies  the  role  of  occluding  boundaries  but  also  integrates  seamlessly  into  our  implicit  reconstruction  framework.The  second  contribution  addresses  the  challenges  of  reconstructing  surfaces  from  raw,  noisy,  and  incomplete  depth  maps-a  common  limitation  of  commercial  depth  cameras.  We  propose  a  variational  framework  that  enforces  global  data  fidelity  while  incorporating  flexible  regularization  strategies.  A  key  innovation  is  the  separation  of  foreground  and  background  modeling,  which  minimizes  the  influence  of  erroneous  background  data.  To  further  mitigate  issues  from  missing  measurements,  we  introduce  a  novel  inpainting  technique  that  works  in  concert  with  an  area-penalty  regularizer.  In  addition,  a  new  initialization  scheme  for  the  implicit  function  is  presented,  accelerating  convergence  and  enhancing  reconstruction  accuracy,  particularly  for  smooth  surfaces.Finally,  we  exploit  the  ideas  from  shape  analysis,  and  develop  a  new  regularizer  for  neural  signed  distance  function  (SDF)  reconstruction.  By  directly  addressing  the  instability  introduced  by  the  prevalent  Eikonal  loss,  our  regularizer  not  only  improves  convergence  but  also  preserves  finer  geometric  details  compared  to  existing  methods.  Rigorous  analysis  and  extensive  experiments  on  public  benchmarks  validate  its  superior  performance.In  summary,  this  dissertation  demonstrates  that  integrating  variational  methods  and  shape  analysis  can  overcome  significant  data-quality  challenges  in  3D  reconstruction,  while  also  offering  new  insights  that  enrich  learning-based  approaches.
■590    ▼aSchool  code:  0078.
■650  4▼aPartial  differential  equations
■650  4▼aDeep  learning
■650  4▼aComputer  vision
■650  4▼aBenchmarks
■650  4▼aDecomposition
■650  4▼aMissing  data
■650  4▼aVisualization
■650  4▼aGeometry
■650  4▼aComputer  science
■690    ▼a0800
■690    ▼a0984
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360338▼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
    TF19147 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.