본문

서브메뉴

Controllable 3D Effects Synthesis in Image Editing
Controllable 3D Effects Synthesis in Image Editing
Controllable 3D Effects Synthesis in Image Editing

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211151409
ISBN  
9798342102117
DDC  
628.9
저자명  
Sheng, Yichen.
서명/저자  
Controllable 3D Effects Synthesis in Image Editing
발행사항  
[Sl] : Purdue University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
119 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
주기사항  
Advisor: Benes, Bedrich.
학위논문주기  
Thesis (Ph.D.)--Purdue University, 2024.
초록/해제  
요약3D effect synthesis is crucial in image editing to enhance realism or visual appeal. Unlike classical graphics rendering, which relies on complete 3D geometries, 3D effect synthesis in image editing operates solely with 2D images as inputs. This shift presents significant challenges, primarily addressed by data-driven methods that learn to synthesize 3D effects in an end-to-end manner. However, these methods face limitations in the diversity of 3D effects they can produce and lack user control. For instance, existing shadow generation networks are restricted to producing hard shadows without offering any user input for customization.In this dissertation, we tackle the research question: how can we synthesize controllable and realistic 3D effects in image editing when only 2D information is available?Our investigation leads to four contributions. First, we introduce a neural network designed to create realistic soft shadows from an image cutout and a user-specified environmental light map. This approach is the first attempt in utilizing neural network for realistic soft shadow rendering in real-time. Second, we develop a novel 2.5D representation Pixel Height, tailored for the nuances of image editing. This representation not only forms the foundation of a new soft shadow rendering pipeline that provides intuitive user control, but also generalizes the soft shadow receivers to be general shadow receivers. Third, we present the mathematical relationship between the Pixel Height representation and 3D space. This connection facilitates the reconstruction of normals or depth from 2D scenes, broadening the scope for synthesizing comprehensive 3D lighting effects such as reflections and refractions. A 3D-aware buffer channels are also proposed to improve the synthesized soft shadow quality. Lastly, we introduce Dr.Bokeh, a differentiable bokeh renderer that extends traditional bokeh effect algorithms with better occlusion modeling to correct flaws existed in existing methods. With the more precise lens modeling, we show that Dr.Bokeh not only achieves the state-of-the-art bokeh rendering quality, but also pushes the boundary of depth-from-defocus problem.Our work in controllable 3D effect synthesis represents a pioneering effort in image editing, laying the groundwork for future lighting effect synthesis in various image editing applications. Moreover, the improvements to filtering-based bokeh rendering could significantly enhance com- mercial products, such as the portrait mode feature on smartphones.
일반주제명  
Lighting
일반주제명  
Realism
일반주제명  
Computer science
기타저자  
Purdue University.
기본자료저록  
Dissertations Abstracts International. 86-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161531
■00520250211151409
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798342102117
■035    ▼a(MiAaPQ)AAI31285314
■035    ▼a(MiAaPQ)25588062
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a628.9
■1001  ▼aSheng,  Yichen.
■24510▼aControllable  3D  Effects  Synthesis  in  Image  Editing
■260    ▼a[Sl]▼bPurdue  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a119  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-05,  Section:  B.
■500    ▼aAdvisor:  Benes,  Bedrich.
■5021  ▼aThesis  (Ph.D.)--Purdue  University,  2024.
■520    ▼a3D  effect  synthesis  is  crucial  in  image  editing  to  enhance  realism  or  visual  appeal.  Unlike  classical  graphics  rendering,  which  relies  on  complete  3D  geometries,  3D  effect  synthesis  in  image  editing  operates  solely  with  2D  images  as  inputs.  This  shift  presents  significant  challenges,  primarily  addressed  by  data-driven  methods  that  learn  to  synthesize  3D  effects  in  an  end-to-end  manner.  However,  these  methods  face  limitations  in  the  diversity  of  3D  effects  they  can  produce  and  lack  user  control.  For  instance,  existing  shadow  generation  networks  are  restricted  to  producing  hard  shadows  without  offering  any  user  input  for  customization.In  this  dissertation,  we  tackle  the  research  question:  how  can  we  synthesize  controllable  and  realistic  3D  effects  in  image  editing  when  only  2D  information  is  available?Our  investigation  leads  to  four  contributions.  First,  we  introduce  a  neural  network  designed  to  create  realistic  soft  shadows  from  an  image  cutout  and  a  user-specified  environmental  light  map.  This  approach  is  the  first  attempt  in  utilizing  neural  network  for  realistic  soft  shadow  rendering  in  real-time.  Second,  we  develop  a  novel  2.5D  representation  Pixel  Height,  tailored  for  the  nuances  of  image  editing.  This  representation  not  only  forms  the  foundation  of  a  new  soft  shadow  rendering  pipeline  that  provides  intuitive  user  control,  but  also  generalizes  the  soft  shadow  receivers  to  be  general  shadow  receivers.  Third,  we  present  the  mathematical  relationship  between  the  Pixel  Height  representation  and  3D  space.  This  connection  facilitates  the  reconstruction  of  normals  or  depth  from  2D  scenes,  broadening  the  scope  for  synthesizing  comprehensive  3D  lighting  effects  such  as  reflections  and  refractions.  A  3D-aware  buffer  channels  are  also  proposed  to  improve  the  synthesized  soft  shadow  quality.  Lastly,  we  introduce  Dr.Bokeh,  a  differentiable  bokeh  renderer  that  extends  traditional  bokeh  effect  algorithms  with  better  occlusion  modeling  to  correct  flaws  existed  in  existing  methods.  With  the  more  precise  lens  modeling,  we  show  that  Dr.Bokeh  not  only  achieves  the  state-of-the-art  bokeh  rendering  quality,  but  also  pushes  the  boundary  of  depth-from-defocus  problem.Our  work  in  controllable  3D  effect  synthesis  represents  a  pioneering  effort  in  image  editing,  laying  the  groundwork  for  future  lighting  effect  synthesis  in  various  image  editing  applications.  Moreover,  the  improvements  to  filtering-based  bokeh  rendering  could  significantly  enhance  com-  mercial  products,  such  as  the  portrait  mode  feature  on  smartphones.
■590    ▼aSchool  code:  0183.
■650  4▼aLighting
■650  4▼aRealism
■650  4▼aComputer  science
■690    ▼a0984
■71020▼aPurdue  University.
■7730  ▼tDissertations  Abstracts  International▼g86-05B.
■790    ▼a0183
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161531▼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
    TF12981 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.