서브메뉴
검색
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
- 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.


