Analyzing style transfer algorithms for segmented images / by Seyed Hadi Seyed.

Author/creator Seyed, Seyed Hadi author.
Other author Hart, David Marvin, degree supervisor.
Other author East Carolina University. Department of Computer Science.
Format Theses and dissertations
Publication[Greenville, N.C.] : [East Carolina University], 2024.
Description1 online resource (45 pages) : color illustrations
Supplemental ContentAccess via ScholarShip
Subjects

Summary The recently developed Segment Anything Model has made grabbing semantically meaningful regions of an image easier than before. This will allow for new applications that build on this approach that weren't previously possible. This thesis investigates integrating the Segment Anything Model with style transfer. Specifically, it proposes Partial Convolution as a way to improve style transfer for segmented regions. Additionally, it investigates how different style transfer techniques are affected by different mask sizes, image statistics, etc.
General notePresented to the Faculty of the Department of Computer Science
General noteAdvisor: David Hart
General noteTitle from PDF t.p. (viewed March 5, 2026).
Dissertation noteM.S. East Carolina University 2024.
Bibliography noteIncludes bibliographical references.
Technical detailsSystem requirements: Adobe Reader.
Technical detailsMode of access: World Wide Web.

Availability

Library Location Call Number Status Item Actions
Electronic Resources Access Content Online ✔ Available