서브메뉴
검색
Exploiting Program Representation with Shader Applications- [electronic resource]
Exploiting Program Representation with Shader Applications- [electronic resource]
- 자료유형
- 학위논문
- Control Number
- 0016932194
- International Standard Book Number
- 9798379716820
- Dewey Decimal Classification Number
- 004
- Main Entry-Personal Name
- Yang, Yuting.
- Publication, Distribution, etc. (Imprint
- [S.l.] : Princeton University., 2023
- Publication, Distribution, etc. (Imprint
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- Physical Description
- 1 online resource(243 p.)
- General Note
- Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
- General Note
- Advisor: Finkelstein, Adam.
- Dissertation Note
- Thesis (Ph.D.)--Princeton University, 2023.
- Restrictions on Access Note
- This item must not be sold to any third party vendors.
- Summary, Etc.
- 요약Programs are widely used in content creation. For example, artists design shader programs to procedurally render scenes and textures, while musicians construct "synth" programs to generate electronic sound. While the generated content is typically the focus of attention, the programs themselves offer hidden potential for transformations that can support untapped applications. In this dissertation, we will discuss four projects that exploit the program structure to automatically apply machine learning or math transformations as if they were manually designed by domain experts. First, we describe a compiler-based framework with novel math rules to extend reverse mode automatic differentiation so as to provide accurate gradients for arbitrary discontinuous programs. The differentiation framework allows us to optimize procedural shader parameters to match target images. Second, we extend the differentiation framework to audio "synth" programs so as to match the acoustic properties of a provided sound clip. We next propose a compiler framework to automatically approximate the convolution of an arbitrary program with a Gaussian kernel in order to smooth the program for visual antialiasing. Finally, we explore the benefit of program representation in deep-learning tasks by proposing to learn from program traces of procedural fragment shaders - programs that generate images. In each of these settings, we demonstrate the benefit of exploiting the program structure to generalize hand-crafted techniques to arbitrary programs.
- Subject Added Entry-Topical Term
- Computer science.
- Subject Added Entry-Topical Term
- Computer engineering.
- Index Term-Uncontrolled
- Automatic differentiation
- Index Term-Uncontrolled
- Compiler
- Index Term-Uncontrolled
- Computer graphics
- Index Term-Uncontrolled
- Differentiable rendering
- Index Term-Uncontrolled
- Machine learning
- Index Term-Uncontrolled
- Programming language
- Added Entry-Corporate Name
- Princeton University Computer Science
- Host Item Entry
- Dissertations Abstracts International. 84-12B.
- Host Item Entry
- Dissertation Abstract International
- Electronic Location and Access
- 로그인을 한후 보실 수 있는 자료입니다.
- Control Number
- joongbu:643937
Buch Status
- Reservierung
- 캠퍼스간 도서대출
- 서가에 없는 책 신고
- Meine Mappe