본문

서브메뉴

Minimal 3D Priors for Sparse View Reconstruction
Minimal 3D Priors for Sparse View Reconstruction
Minimal 3D Priors for Sparse View Reconstruction

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105212
ISBN  
9798291564776
DDC  
004
저자명  
Rockwell, Chris.
서명/저자  
Minimal 3D Priors for Sparse View Reconstruction
발행사항  
[Sl] : University of Michigan, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
173 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
주기사항  
Advisor: Fouhey, David F.;Johnson, Justin.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2025.
초록/해제  
요약Sparse view reconstruction is a fundamental problem in computer vision with applications in extended reality, generative AI and robotics. Unfortunately, while learned methods have found great success in 2D and more recently dense view 3D, obtaining 3D from sparse views is an under-constrained problem challenging state-of-the-art models. The overarching idea of this dissertation is that we need only to introduce minimal 3D priors to these learned methods to significantly improve sparse view performance. We focus on the central tasks of novel view synthesis and relative camera pose estimation, proposing state-of-the-art published frameworks containing thorough comparison with prior methods and ablations, confirming the effectiveness of the proposed 3D priors. "PixelSynth" approaches the task of novel view synthesis across large view changes given a single image. This is a challenging task requiring the model to imagine new content, and produce it in a manner consistent with other generated views. While prior work is not up to this task, our contribution of 3D-Consistent Scene Extrapolation achieves high-quality and consistent extrapolations by incorporating a 3D representation into a generative model. "The 8-Point ViT" estimates relative camera pose, including scale, from a pair of wide-baseline images. We show adding minimal 3D Priors can enable a ViT block to compute entries used in the classical 8-Point Algorithm, leading to large gains over prior work, particularly in the case of limited data. We refer to this as Geometry-Guided Relative Pose Estimation. We further improve pose performance in "FAR." It uses the key insight that learned methods like "The 8-Point ViT" tend to be relatively robust, while classical correspondence solvers tend to be relatively precise. "FAR" utilizes the best of both methods in an adaptable design, producing "Flexible, Accurate and Robust" pose estimation. Finally, we apply a similar combination of 3D solvers with learned methods to the case of dense views. Armed with more views, we show state-of-the-art results in the highly challenging case of dynamic Internet video, and collect the largest publicly available diverse, dynamic camera pose dataset "DynPose-100K".
일반주제명  
Computer science
일반주제명  
Computer engineering
키워드  
3D computer vision
키워드  
Sparse view reconstruction
키워드  
3D priors
키워드  
Camera pose
기타저자  
University of Michigan Computer Science & Engineering
기본자료저록  
Dissertations Abstracts International. 87-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359779
■00520260202105212
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291564776
■035    ▼a(MiAaPQ)AAI32271721
■035    ▼a(MiAaPQ)umichrackham006253
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aRockwell,  Chris.
■24510▼aMinimal  3D  Priors  for  Sparse  View  Reconstruction
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a173  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-02,  Section:  B.
■500    ▼aAdvisor:  Fouhey,  David  F.;Johnson,  Justin.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2025.
■520    ▼aSparse  view  reconstruction  is  a  fundamental  problem  in  computer  vision  with  applications  in  extended  reality,  generative  AI  and  robotics.  Unfortunately,  while  learned  methods  have  found  great  success  in  2D  and  more  recently  dense  view  3D,  obtaining  3D  from  sparse  views  is  an  under-constrained  problem  challenging  state-of-the-art  models.  The  overarching  idea  of  this  dissertation  is  that  we  need  only  to  introduce  minimal  3D  priors  to  these  learned  methods  to  significantly  improve  sparse  view  performance.  We  focus  on  the  central  tasks  of  novel  view  synthesis  and  relative  camera  pose  estimation,  proposing  state-of-the-art  published  frameworks  containing  thorough  comparison  with  prior  methods  and  ablations,  confirming  the  effectiveness  of  the  proposed  3D  priors.  "PixelSynth"  approaches  the  task  of  novel  view  synthesis  across  large  view  changes  given  a  single  image.  This  is  a  challenging  task  requiring  the  model  to  imagine  new  content,  and  produce  it  in  a  manner  consistent  with  other  generated  views.  While  prior  work  is  not  up  to  this  task,  our  contribution  of  3D-Consistent  Scene  Extrapolation  achieves  high-quality  and  consistent  extrapolations  by  incorporating  a  3D  representation  into  a  generative  model.  "The  8-Point  ViT"  estimates  relative  camera  pose,  including  scale,  from  a  pair  of  wide-baseline  images.  We  show  adding  minimal  3D  Priors  can  enable  a  ViT  block  to  compute  entries  used  in  the  classical  8-Point  Algorithm,  leading  to  large  gains  over  prior  work,  particularly  in  the  case  of  limited  data.  We  refer  to  this  as  Geometry-Guided  Relative  Pose  Estimation.  We  further  improve  pose  performance  in  "FAR."  It  uses  the  key  insight  that  learned  methods  like  "The  8-Point  ViT"  tend  to  be  relatively  robust,  while  classical  correspondence  solvers  tend  to  be  relatively  precise.  "FAR"  utilizes  the  best  of  both  methods  in  an  adaptable  design,  producing  "Flexible,  Accurate  and  Robust"  pose  estimation.  Finally,  we  apply  a  similar  combination  of  3D  solvers  with  learned  methods  to  the  case  of  dense  views.  Armed  with  more  views,  we  show  state-of-the-art  results  in  the  highly  challenging  case  of  dynamic  Internet  video,  and  collect  the  largest  publicly  available  diverse,  dynamic  camera  pose  dataset  "DynPose-100K".
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■653    ▼a3D  computer  vision
■653    ▼aSparse  view  reconstruction
■653    ▼a3D  priors
■653    ▼aCamera  pose
■690    ▼a0984
■690    ▼a0464
■690    ▼a0800
■71020▼aUniversity  of  Michigan▼bComputer  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-02B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359779▼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
    TF15282 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.