본문

서브메뉴

Efficient 3D Perception From Images
Efficient 3D Perception From Images
Efficient 3D Perception From Images

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103609
ISBN  
9798288862502
DDC  
620
저자명  
Li, Ruilong.
서명/저자  
Efficient 3D Perception From Images
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
74 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Kanazawa, Angjoo.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약The ability to capture, reconstruct, and interact with the world in three dimensions is transforming how we experience, understand, and shape our environment. From virtual reality and digital heritage to robotics and scientific discovery, 3D perception is opening new frontiers across art, science, and technology. Yet, despite remarkable progress, creating high-fidelity 3D models from images remains a computationally demanding challenge-one that limits the accessibility and scalability of these powerful tools.This thesis addresses the core bottleneck of efficiency in differentiable volume rendering, a foundational technique behind recent breakthroughs such as Neural Radiance Fields (NeRF) and Gaussian Splatting. While these methods have demonstrated that continuous volumetric representations and differentiable rendering pipelines can achieve photorealistic results from sparse or unconstrained inputs, their high computational and memory costs pose significant barriers to real-time and large-scale applications.To overcome these challenges, I present a series of algorithmic and systems-level innovations aimed at making 3D perception faster, more scalable, and more practical. First, I introduce compact and expressive scene representations that reduce memory overhead without sacrificing quality. Second, I develop smarter sampling and visibility strategies that exploit the inherent sparsity of 3D space, focusing computation where it matters most. Third, I design parallelization techniques tailored for modern multi-GPU systems, enabling distributed training and rendering at unprecedented scales. Finally, I explore learning-based approaches that leverage multi-view geometry and attention mechanisms to further accelerate and generalize 3D perception.Through a combination of theoretical insights, open-source tools, and empirical validation, this work charts a path toward real-time, high-resolution 3D reconstruction that is accessible beyond specialized labs and supercomputers. By making 3D perception more efficient, this thesis aims to unlock new possibilities and bring us closer to a future where anyone can capture, share, and explore the spaces they love in all their depth and richness.
일반주제명  
Engineering
일반주제명  
Computer science
일반주제명  
Information technology
키워드  
3D perception
키워드  
Deep learning
키워드  
Neural rendering
키워드  
Reconstruction
키워드  
Neural Radiance Fields
기타저자  
University of California, Berkeley Computer Science
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357855
■00520260202103609
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288862502
■035    ▼a(MiAaPQ)AAI32043045
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a620
■1001  ▼aLi,  Ruilong.
■24510▼aEfficient  3D  Perception  From  Images
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a74  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Kanazawa,  Angjoo.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aThe  ability  to  capture,  reconstruct,  and  interact  with  the  world  in  three  dimensions  is  transforming  how  we  experience,  understand,  and  shape  our  environment.  From  virtual  reality  and  digital  heritage  to  robotics  and  scientific  discovery,  3D  perception  is  opening  new  frontiers  across  art,  science,  and  technology.  Yet,  despite  remarkable  progress,  creating  high-fidelity  3D  models  from  images  remains  a  computationally  demanding  challenge-one  that  limits  the  accessibility  and  scalability  of  these  powerful  tools.This  thesis  addresses  the  core  bottleneck  of  efficiency  in  differentiable  volume  rendering,  a  foundational  technique  behind  recent  breakthroughs  such  as  Neural  Radiance  Fields  (NeRF)  and  Gaussian  Splatting.  While  these  methods  have  demonstrated  that  continuous  volumetric  representations  and  differentiable  rendering  pipelines  can  achieve  photorealistic  results  from  sparse  or  unconstrained  inputs,  their  high  computational  and  memory  costs  pose  significant  barriers  to  real-time  and  large-scale  applications.To  overcome  these  challenges,  I  present  a  series  of  algorithmic  and  systems-level  innovations  aimed  at  making  3D  perception  faster,  more  scalable,  and  more  practical.  First,  I  introduce  compact  and  expressive  scene  representations  that  reduce  memory  overhead  without  sacrificing  quality.  Second,  I  develop  smarter  sampling  and  visibility  strategies  that  exploit  the  inherent  sparsity  of  3D  space,  focusing  computation  where  it  matters  most.  Third,  I  design  parallelization  techniques  tailored  for  modern  multi-GPU  systems,  enabling  distributed  training  and  rendering  at  unprecedented  scales.  Finally,  I  explore  learning-based  approaches  that  leverage  multi-view  geometry  and  attention  mechanisms  to  further  accelerate  and  generalize  3D  perception.Through  a  combination  of  theoretical  insights,  open-source  tools,  and  empirical  validation,  this  work  charts  a  path  toward  real-time,  high-resolution  3D  reconstruction  that  is  accessible  beyond  specialized  labs  and  supercomputers.  By  making  3D  perception  more  efficient,  this  thesis  aims  to  unlock  new  possibilities  and  bring  us  closer  to  a  future  where  anyone  can  capture,  share,  and  explore  the  spaces  they  love  in  all  their  depth  and  richness.
■590    ▼aSchool  code:  0028.
■650  4▼aEngineering
■650  4▼aComputer  science
■650  4▼aInformation  technology
■653    ▼a3D  perception
■653    ▼aDeep  learning
■653    ▼aNeural  rendering
■653    ▼aReconstruction
■653    ▼aNeural  Radiance  Fields
■690    ▼a0800
■690    ▼a0489
■690    ▼a0984
■690    ▼a0537
■71020▼aUniversity  of  California,  Berkeley▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357855▼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
    TF14878 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.