본문

서브메뉴

Object and Scene Reconstruction Using Neural Radiance Fields- [electronic resource]
Object and Scene Reconstruction Using Neural Radiance Fields - [electronic resource]
Object and Scene Reconstruction Using Neural Radiance Fields- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100501
ISBN  
9798380879279
DDC  
004
저자명  
Tancik, Matthew.
서명/저자  
Object and Scene Reconstruction Using Neural Radiance Fields - [electronic resource]
발행사항  
[S.l.]: : University of California, Berkeley., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(116 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
주기사항  
Advisor: Kanazawa, Angjoo;Ng, Ren.
학위논문주기  
Thesis (D.Eng.)--University of California, Berkeley, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약This dissertation explores the synthesis of novel views of complex scenes through the optimization of a volumetric scene function using a sparse set of input views. Our approach represents the scene as a neural radiance field (NeRF), a field of densities and emitted radiance based on 5D coordinates encompassing spatial location (x, y, z) and viewing direction (θ, φ). NeRF enables the rendering of photorealistic novel views that surpass previous techniques, leading to numerous follow-ups and extensions in the computer vision and graphics communities. To enhance the representation of high-frequency details in NeRFs, we introduce a Fourier feature mapping technique that effectively learns high-frequency functions within low-dimensional problem domains, including NeRF. We demonstrate the benefits of leveraging learned initial weight parameters through standard meta-learning algorithms, resulting in accelerated convergence, stronger priors, and improved generalization for coordinate-based networks. In addition, we improve the scalability of NeRFs with a proposed method capable of representing arbitrarily large scenes. This method enables city-scale reconstructions using data captured under diverse environmental conditions. Finally, we present the Nerfstudio framework, a comprehensive suite of modular components and tools designed for the development and deployment of NeRF-based methods. This framework empowers researchers and practitioners with real-time visualization, streamlined data pipelines, and export capabilities, facilitating the democratization of NeRFs and extending their impact beyond research settings. With their potential to transform computer graphics, virtual reality, augmented reality, and other domains, NeRFs hold promise for revolutionizing the way we perceive and interact with digital worlds.
일반주제명  
Computer science.
일반주제명  
Computer engineering.
일반주제명  
Information technology.
키워드  
Scene reconstruction
키워드  
Object
키워드  
Neural radiance field
키워드  
Spatial location
키워드  
Nerfstudio
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 85-06B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016932464
■00520240214100501
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380879279
■035    ▼a(MiAaPQ)AAI30492937
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aTancik,  Matthew.
■24510▼aObject  and  Scene  Reconstruction  Using  Neural  Radiance  Fields▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Berkeley.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(116  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-06,  Section:  B.
■500    ▼aAdvisor:  Kanazawa,  Angjoo;Ng,  Ren.
■5021  ▼aThesis  (D.Eng.)--University  of  California,  Berkeley,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aThis  dissertation  explores  the  synthesis  of  novel  views  of  complex  scenes  through  the  optimization  of  a  volumetric  scene  function  using  a  sparse  set  of  input  views.  Our  approach  represents  the  scene  as  a  neural  radiance  field  (NeRF),  a  field  of  densities  and  emitted  radiance  based  on  5D  coordinates  encompassing  spatial  location  (x,  y,  z)  and  viewing  direction  (θ,  φ).  NeRF  enables  the  rendering  of  photorealistic  novel  views  that  surpass  previous  techniques,  leading  to  numerous  follow-ups  and  extensions  in  the  computer  vision  and  graphics  communities.  To  enhance  the  representation  of  high-frequency  details  in  NeRFs,  we  introduce  a  Fourier  feature  mapping  technique  that  effectively  learns  high-frequency  functions  within  low-dimensional  problem  domains,  including  NeRF.  We  demonstrate  the  benefits  of  leveraging  learned  initial  weight  parameters  through  standard  meta-learning  algorithms,  resulting  in  accelerated  convergence,  stronger  priors,  and  improved  generalization  for  coordinate-based  networks.  In  addition,  we  improve  the  scalability  of  NeRFs  with  a  proposed  method  capable  of  representing  arbitrarily  large  scenes.  This  method  enables  city-scale  reconstructions  using  data  captured  under  diverse  environmental  conditions.  Finally,  we  present  the  Nerfstudio  framework,  a  comprehensive  suite  of  modular  components  and  tools  designed  for  the  development  and  deployment  of  NeRF-based  methods.  This  framework  empowers  researchers  and  practitioners  with  real-time  visualization,  streamlined  data  pipelines,  and  export  capabilities,  facilitating  the  democratization  of  NeRFs  and  extending  their  impact  beyond  research  settings.  With  their  potential  to  transform  computer  graphics,  virtual  reality,  augmented  reality,  and  other  domains,  NeRFs  hold  promise  for  revolutionizing  the  way  we  perceive  and  interact  with  digital  worlds.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science.
■650  4▼aComputer  engineering.
■650  4▼aInformation  technology.
■653    ▼aScene  reconstruction
■653    ▼aObject
■653    ▼aNeural  radiance  field
■653    ▼aSpatial  location
■653    ▼aNerfstudio
■690    ▼a0984
■690    ▼a0489
■690    ▼a0464
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g85-06B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0028
■791    ▼aD.Eng.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932464▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

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
    TF08066 전자도서 마이폴더 부재도서신고 비도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.