Back to search

Rochester Institute of Technology

Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation

Abstract

dc:description.abstract

Image-to-Image translation is the task of translating images between domains while maintaining the identity of the images. The task can be used for entertainment purposes and applications, data augmentation, semantic image segmentation, and more. Generative Adversarial Networks (GANs), and in particular Conditional GANs have recently shown incredible success in image-to-image translation and semantic manipulation. However, such methods require paired data, meaning that an image must have ground-truth translations across domains. Cycle-consistent GANs solve this problem by using unpaired data. Such methods work well for translations that involve color and texture changes but fail when shape changes are required. This research analyzes the trade-offs between the cycle-consistency importance and the necessary shape changes required for natural looking imagery. The research proposes simple architectural and loss changes to maintain cycle-consistency strength while allowing the model to perform shape changes as required. The results demonstrate improved translations between domains that require shape changes while preserving performance between domains that don’t require shape changes.

Degree

thesis:*
Name thesis:degree_name
Computer Engineering (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Computer Engineering (KGCOE)

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Longman, Ram
Contributors dc:contributor
  • Raymond Ptucha

Subjects

dc:subject × 4

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.rit.edu/theses/9939

Chain of custody

source
Harvested from
Rochester Institute of Technology
Base URL
repository.rit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Longman, Ram. Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation. Thesis thesis, https://repository.rit.edu/theses/9939