서브메뉴
검색
Task-specific Computational Cameras
Task-specific Computational Cameras
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151420
- ISBN
- 9798382806723
- DDC
- 004
- 저자명
- Shi, Zheng.
- 서명/저자
- Task-specific Computational Cameras
- 발행사항
- [Sl] : Princeton University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 180 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Heide, Felix.
- 학위논문주기
- Thesis (Ph.D.)--Princeton University, 2024.
- 초록/해제
- 요약Machine vision, while fundamentally relying on images as inputs, has traditionally treated image acquisition and image processing as two separate tasks. However, traditional image acquisition systems are tuned for aesthetics, i.e. photos that please the human eye, and not computational tasks that requires beyond human vision. My research focuses on developing task-specific computational imaging systems to enable the capture of information that extends beyond the capabilities of standard RGB cameras, thereby enhancing the effectiveness of downstream machine vision applications.This thesis begins with combining multiple imaging modalities to facilitate training on unpaired real-world datasets, addressing the scarcity of supervised training data. We introduce ZeroScatter, a single-image descattering method capable of removing adverse weather effects from RGB captures. By integrating model-based, temporal, and multi-view cues, as well as information contained in gated imager captures, we offer indirect supervision for training on real-world adverse weather captures lacking ground truth. This approach significantly enhances generalizability on unseen data, surpassing methods trained exclusively on synthetic adverse weather data.Relying solely on conventional RBG image inputs, while more broadly applicable, limits the available information, thus requiring the model to fill in gaps by generating plausible inferences based on learnt prior, such as when car window wiper obscure objects from the dash cameras. To bypass these constraints, we shift towards computational cameras, and design specialized flat optics to boost the capabilities of cameras for a range of applications.We first propose a computational monocular camera that optically cloaks unwanted near-camera obstructions. We learn a custom diffractive optical element (DOE) that performs depth-dependent optical encoding, scattering nearby occlusions while enabling focus on paraxial wavefronts emanating from background objects. This allows us to computationally reconstruct unobstructed images without different camera views or hallucinations.Lastly, we introduce a split-aperture 2-in-1 computational camera that combines application-specific optical modulation with conventional imaging into one system. This approach simplifies complex inverse problems faced by computational cameras, enhances reconstruction quality, and offers a real-time viewfinder experience; paving the way for the adoption of computational camera technology in consumer devices.
- 일반주제명
- Computer science
- 일반주제명
- Information technology
- 일반주제명
- Optics
- 키워드
- Cameras
- 기타저자
- Princeton University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161608
■00520250211151420
■006m o d
■007cr#unu||||||||
■020 ▼a9798382806723
■035 ▼a(MiAaPQ)AAI31294108
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aShi, Zheng.▼0(orcid)0000-0002-9919-8816
■24510▼aTask-specific Computational Cameras
■260 ▼a[Sl]▼bPrinceton University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a180 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Heide, Felix.
■5021 ▼aThesis (Ph.D.)--Princeton University, 2024.
■520 ▼aMachine vision, while fundamentally relying on images as inputs, has traditionally treated image acquisition and image processing as two separate tasks. However, traditional image acquisition systems are tuned for aesthetics, i.e. photos that please the human eye, and not computational tasks that requires beyond human vision. My research focuses on developing task-specific computational imaging systems to enable the capture of information that extends beyond the capabilities of standard RGB cameras, thereby enhancing the effectiveness of downstream machine vision applications.This thesis begins with combining multiple imaging modalities to facilitate training on unpaired real-world datasets, addressing the scarcity of supervised training data. We introduce ZeroScatter, a single-image descattering method capable of removing adverse weather effects from RGB captures. By integrating model-based, temporal, and multi-view cues, as well as information contained in gated imager captures, we offer indirect supervision for training on real-world adverse weather captures lacking ground truth. This approach significantly enhances generalizability on unseen data, surpassing methods trained exclusively on synthetic adverse weather data.Relying solely on conventional RBG image inputs, while more broadly applicable, limits the available information, thus requiring the model to fill in gaps by generating plausible inferences based on learnt prior, such as when car window wiper obscure objects from the dash cameras. To bypass these constraints, we shift towards computational cameras, and design specialized flat optics to boost the capabilities of cameras for a range of applications.We first propose a computational monocular camera that optically cloaks unwanted near-camera obstructions. We learn a custom diffractive optical element (DOE) that performs depth-dependent optical encoding, scattering nearby occlusions while enabling focus on paraxial wavefronts emanating from background objects. This allows us to computationally reconstruct unobstructed images without different camera views or hallucinations.Lastly, we introduce a split-aperture 2-in-1 computational camera that combines application-specific optical modulation with conventional imaging into one system. This approach simplifies complex inverse problems faced by computational cameras, enhances reconstruction quality, and offers a real-time viewfinder experience; paving the way for the adoption of computational camera technology in consumer devices.
■590 ▼aSchool code: 0181.
■650 4▼aComputer science
■650 4▼aInformation technology
■650 4▼aOptics
■653 ▼aComputational imaging
■653 ▼aComputational optics
■653 ▼aStereo consistency
■653 ▼aDiffractive optical element
■653 ▼aCameras
■690 ▼a0984
■690 ▼a0752
■690 ▼a0489
■690 ▼a0800
■71020▼aPrinceton University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0181
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161608▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
