자료유형  

 학위논문

Control Number  

0017162740

International Standard Book Number  

9798342106627

Dewey Decimal Classification Number  

620.004

Main Entry-Personal Name  

May, Christopher.

Publication, Distribution, etc. (Imprint  

[S.l.] : Purdue University., 2024

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2024

Physical Description  

68 p.

General Note  

Source: Dissertations Abstracts International, Volume: 86-04, Section: B.

General Note  

Advisor: Aliaga, Daniel.

Dissertation Note  

Thesis (Ph.D.)--Purdue University, 2024.

Summary, Etc.  

요약Omnidirectional images are a way to visualize an environment in all directions. They have a spherical topology and require careful attention when represented by a computer. Namely, mapping the sphere to a plane introduces stretching of the spherical image content, and requires at least one seam in the image to be able to unwrap the sphere. Generative neural networks have shown impressive ability to synthesize images, but generating spherical images is still challenging. Without specific handling of the spherical topology, the generated images often exhibit distorted contents and discontinuities across the seams. We describe strategies for mitigating such distortions during image generation, as well as ensuring the image remains continuous across all boundaries. Our solutions can be applied to a variety of spherical image representations, including cube-maps and equirectangular projections.A closely related problem in generative networks is 3D-aware scene generation, wherein the task involves the creation of an environment in which the viewpoint can be directly controlled. Many NeRF-based solutions have been proposed, but they generally focus on generation of single objects or faces. Full 3D environments are more difficult to synthesize and are less studied. We approach this problem by leveraging omnidirectional image synthesis, using the initial features of the network as a transformable foundation upon which to build the scene. By translating within the initial feature space, we correspondingly translate in the output omnidirectional image, preserving the scene characteristics. We additionally develop a regularizing loss based on epipolar geometry to encourage geometric consistency between viewpoints. We demonstrate the effectiveness of our method with a structure-from-motion-based reconstruction metric, along with comparisons to related works.

Subject Added Entry-Topical Term  

Layouts.

Subject Added Entry-Topical Term  

Computer & video games.

Subject Added Entry-Topical Term  

Cartography.

Subject Added Entry-Topical Term  

Geometry.

Subject Added Entry-Topical Term  

Virtual reality.

Subject Added Entry-Topical Term  

Neural networks.

Subject Added Entry-Topical Term  

Computer science.

Subject Added Entry-Topical Term  

Information technology.

Added Entry-Corporate Name  

Purdue University.

Host Item Entry  

Dissertations Abstracts International. 86-04B.

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:657805