Abstract
Image datasets often live on a continuum: Images from an outdoor scene vary from day to night, across different weather conditions, and over the course of seasons. Faces age and exhibit different expressions. We consider the problem of taking individual images from these datasets and explicitly manipulating those images to change where they lie on the continuum. We focus on a version of this problem that requires as little input as possible, and we build off of previous work using CNN features to construct an intermediate image manifold on which to manipulate the images. We also investigate a novel way of reconstructing images from their CNN features using alpha compositions of the input images. These technique produce convincing semantic interpolations of images and timelapse video from a variety of sources.
Committee Chair
Robert Pless
Committee Members
Tao Ju William Richard
Degree
Master of Science (MS)
Author's Department
Computer Science & Engineering
Document Type
Thesis
Date of Award
Summer 2016
Language
English (en)
DOI
https://doi.org/10.7936/K7VH5M3V
Author's ORCID
https://orcid.org/0000-0002-8985-1084
Recommended Citation
Little, Joshua D., "Deep Semantic Image Interpolation" (2016). McKelvey School of Engineering Theses & Dissertations. 151.
The definitive version is available at https://doi.org/10.7936/K7VH5M3V
Comments
Permanent URL: https://doi.org/10.7936/K7VH5M3V