Abstract
dc:description.abstractDeep Learning has made tremendous progress in the last decade, making breakthroughs in visual perception and imagination. Discriminative models have achieved human-level performance on several tasks. Generative models have also shown great promise for 2D and 3D synthesis; however, their performance still lags behind discriminative models. Several approaches have been proposed to enhance the performance of generative models. One promising direction is leveraging multiple representations to guide the synthesis process. In this dissertation, we explore how generative models can benefit from hybrid representations, in which a stronger representation guides a weaker one. We propose models for 3D synthesis conditioned on images or point clouds, label-conditioned 2D generation, and 2.5D motion generation. A major drawback of current generative models is that they require gigantic datasets for training. We present a few-shot synthesis method for decreasing the model’s dependence on labeled data. Finally, we discuss adversarial applications of generative models in which adversaries abuse visual realism to deceive humans and machines.
Degree
thesis:*- Name thesis:degree_name
- Ph. D., Electrical and Computer Engineering
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Electrical and Computer Engineering
- Grantor
- Cornell University
- Year dc:date.issued
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Poursaeed, Omid
- Chair dc:contributor.chair
-
- Belongie, Serge J.
- Committee members dc:contributor.committeemember
-
- Joachims, Thorsten
- Zabih, Ramin
Subjects
dc:subject × 6Rights
dc:rights- Statement dc:rights
-
- Attribution 4.0 International
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 13277989
- Dc Identifier Other
-
ProQuest Submission ID: 12239
ProQuest Publication ID: 28088959