Exemplar-based image inpainting on the GPU applied to 3D video conversion

Simple item page
dc.contributor.authorWallace, Ryan
dc.contributor.supervisorGooch, Amy
dc.date.accessioned2012-02-22T17:09:25Z
dc.date.copyright2011en_US
dc.date.issued2012-02-22
dc.degree.departmentDepartment of Computer Science
dc.degree.levelMaster of Science M.Sc.en_US
dc.description.abstractMy thesis investigates automation and optimizations for occlusion filling, a problem resulting from the generation of new viewpoints in the 3D video conversion process. Image inpainting is a popular topic in image processing research. The ability to fill a region of an image in a manner that is visually pleasing is a difficult and computationally expensive task. Recently, the most successful methods have been exemplar-based, copying patches of the image from a specified source region into the region to be filled. These algorithms are designed to propagate both structure and texture into the fill region. They are brute force algorithms however, and are generally implemented as sequential algorithms to be run on the CPU. In this research, I have effectively mapped the costly portions of an exemplar-based image inpainting algorithm to the GPU. I produce equivalent inpainting results in less time by parallelizing the brute force patch searching portion of the algorithm. Furthermore, I compare the results with another recent, optimized inpainting algorithm, and apply both algorithms to the real world problem of occlusion filling in a 3D video conversion pipeline.en_US
dc.description.scholarlevelGraduateen_US
dc.identifier.urihttp://hdl.handle.net/1828/3843
dc.languageEnglisheng
dc.language.isoenen_US
dc.rights.tempAvailable to the World Wide Weben_US
dc.subjectInpaintingen_US
dc.subject3D Conversionen_US
dc.subjectGPUen_US
dc.titleExemplar-based image inpainting on the GPU applied to 3D video conversionen_US
dc.typeThesisen_US

Files

License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.74 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Electronic Theses and Dissertations (ETD)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.