본문

서브메뉴

Open-World 3D Understanding and Generation
Open-World 3D Understanding and Generation
Open-World 3D Understanding and Generation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152815
ISBN  
9798346808664
DDC  
004
저자명  
Liu, Minghua.
서명/저자  
Open-World 3D Understanding and Generation
발행사항  
[Sl] : University of California, San Diego, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
193 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-06, Section: A.
주기사항  
Advisor: Su, Hao.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2024.
초록/해제  
요약3D representations model our physical world in one of the most explicit and structured ways, enabling the storage of extensive attributes. Understanding these 3D representations-including, but not limited to, their geometry, appearance, structure, semantics, mobility, functionality, and affordances-is crucial for developing intelligent agents that can comprehend and interact with our 3D physical environment and seamlessly integrate into human settings. Additionally, high-quality 3D generation allows us to replicate our 3D world, creating digital twins and supporting a wide range of downstream applications. Significant advancements have already been made in 3D deep learning by exploring suitable representations and neural algorithms for 3D data. However, unlike many other modalities, the scale of publicly available 3D data has been quite limited. Most previous 3D deep learning approaches have traditionally been confined to a narrow range of common categories (such as chairs, cars, airplanes, etc.), which greatly hinders their application to real-world scenarios with far more diverse categories and variations. Nevertheless, in the past two years, with the rapid development of large-scale pretrained models from 2D vision, language, and other modalities, as well as the emergence of larger and more diverse public 3D datasets, many new opportunities for 3D deep learning have arisen.In this dissertation, we explore how to leverage extensive priors from other modalities, as well as how to exploit the limited but valuable 3D data to enhance the generalizability of various 3D deep learning tasks. We primarily focus on two families of tasks: 3D object understanding and 3D object generation in an open-world context. For each family, I explore several strategies to effectively utilize these priors and identify a series of crucial problems with proposed solutions. My efforts have significantly improved the generalizability of many previous 3D understanding and generation tasks, bridging the gap between the capabilities of earlier 'chair research' and the complex, diverse open-world scenarios in the real physical 3D world.
일반주제명  
Computer science
일반주제명  
Computer engineering
일반주제명  
Design
키워드  
3D representations
키워드  
3D generation
키워드  
Deep learning
키워드  
3D world
기타저자  
University of California, San Diego Computer Science and Engineering
기본자료저록  
Dissertations Abstracts International. 86-06A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163968
■00520250211152815
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346808664
■035    ▼a(MiAaPQ)AAI31558660
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aLiu,  Minghua.
■24510▼aOpen-World  3D  Understanding  and  Generation
■260    ▼a[Sl]▼bUniversity  of  California,  San  Diego▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a193  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-06,  Section:  A.
■500    ▼aAdvisor:  Su,  Hao.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2024.
■520    ▼a3D  representations  model  our  physical  world  in  one  of  the  most  explicit  and  structured  ways,  enabling  the  storage  of  extensive  attributes.  Understanding  these  3D  representations-including,  but  not  limited  to,  their  geometry,  appearance,  structure,  semantics,  mobility,  functionality,  and  affordances-is  crucial  for  developing  intelligent  agents  that  can  comprehend  and  interact  with  our  3D  physical  environment  and  seamlessly  integrate  into  human  settings.  Additionally,  high-quality  3D  generation  allows  us  to  replicate  our  3D  world,  creating  digital  twins  and  supporting  a  wide  range  of  downstream  applications.  Significant  advancements  have  already  been  made  in  3D  deep  learning  by  exploring  suitable  representations  and  neural  algorithms  for  3D  data.  However,  unlike  many  other  modalities,  the  scale  of  publicly  available  3D  data  has  been  quite  limited.  Most  previous  3D  deep  learning  approaches  have  traditionally  been  confined  to  a  narrow  range  of  common  categories  (such  as  chairs,  cars,  airplanes,  etc.),  which  greatly  hinders  their  application  to  real-world  scenarios  with  far  more  diverse  categories  and  variations.  Nevertheless,  in  the  past  two  years,  with  the  rapid  development  of  large-scale  pretrained  models  from  2D  vision,  language,  and  other  modalities,  as  well  as  the  emergence  of  larger  and  more  diverse  public  3D  datasets,  many  new  opportunities  for  3D  deep  learning  have  arisen.In  this  dissertation,  we  explore  how  to  leverage  extensive  priors  from  other  modalities,  as  well  as  how  to  exploit  the  limited  but  valuable  3D  data  to  enhance  the  generalizability  of  various  3D  deep  learning  tasks.  We  primarily  focus  on  two  families  of  tasks:  3D  object  understanding  and  3D  object  generation  in  an  open-world  context.  For  each  family,  I  explore  several  strategies  to  effectively  utilize  these  priors  and  identify  a  series  of  crucial  problems  with  proposed  solutions.  My  efforts  have  significantly  improved  the  generalizability  of  many  previous  3D  understanding  and  generation  tasks,  bridging  the  gap  between  the  capabilities  of  earlier  'chair  research'  and  the  complex,  diverse  open-world  scenarios  in  the  real  physical  3D  world.
■590    ▼aSchool  code:  0033.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■650  4▼aDesign
■653    ▼a3D  representations
■653    ▼a3D  generation
■653    ▼aDeep  learning
■653    ▼a3D  world
■690    ▼a0984
■690    ▼a0389
■690    ▼a0464
■690    ▼a0800
■71020▼aUniversity  of  California,  San  Diego▼bComputer  Science  and  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-06A.
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163968▼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
    TF09999 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.