Return to search

Unpaired Skeleton-to-Photo Translation for Sketch-to-Photo Synthesis

Sketch-to-photo synthesis usually faced the problem of lack of labeled data, so we propose some methods based on CycleGAN to train a model to translate sketch to photo with unpaired data. Our main contribution is a proposed Sketch-to-Skeleton-to-Image (SSI) method, which performs skeletonization on sketches to reduce variance on the sketch data. We also tried different representations of the skeleton and different models for our task. Experiment results show that the generated image quality has a negative correlation with the sparsity of the input data.

Identiferoai:union.ndltd.org:UMASS/oai:scholarworks.umass.edu:masters_theses_2-2302
Date28 October 2022
CreatorsGu, Yuanzhe
PublisherScholarWorks@UMass Amherst
Source SetsUniversity of Massachusetts, Amherst
Detected LanguageEnglish
Typetext
Formatapplication/pdf
SourceMasters Theses

Page generated in 0.0017 seconds