서브메뉴
검색
Object and Scene Reconstruction Using Neural Radiance Fields- [electronic resource]
Object and Scene Reconstruction Using Neural Radiance Fields- [electronic resource]
Detailed Information
- 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
- Object
- 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
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Подробнее информация.
- Бронирование
- не существует
- моя папка
- Первый запрос зрения
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.
![Object and Scene Reconstruction Using Neural Radiance Fields - [electronic resource]](/Users/Baul/Images/book.png)

