Paper Info
Title
An Extensive Study of Cycle-Consistent Generative Networks for Image-to-Image Translation
Abstract
Image-to-image translation between different domains has been an important research direction, with the aim of arbitrarily manipulating the source image content to become similar to a target image. Recently, cycle-consistent generative network (CycleGAN) has become a fundamental approach for general-purpose image-to-image translation, while almost no work has examined what factors may influence its performance. To provide more insights, we propose two new models roughly based on CycleGAN, namely Long CycleGAN and Nest CycleGAN. First, Long CycleGAN cascades several generators to perform the domain translation in a long cycle. It shows the benefit of stacking more generators on the generation quality. In addition to the long cycle, Nest CycleGAN develops new inner cycles to bridge intermediate generators directly, which can help constrain the unsupervised mappings. In the experiments, we conduct qualitative and quantitative comparisons for tasks including photo↔label, photo↔sketch, and photo colorization. The quantitative and qualitative results demonstrate the effectiveness of our two proposed models.
Year
DOI
Venue
2018
10.1109/ICPR.2018.8545089
2018 24th International Conference on Pattern Recognition (ICPR)
Keywords
Field
DocType
cycle-consistent generative network,source image content,target image,general-purpose image-to-image translation,Long CycleGAN,Nest CycleGAN,domain translation,long cycle,generation quality,bridge intermediate generators
Image translation,Iterative reconstruction,Computer vision,Task analysis,Pattern recognition,Computer science,Image content,Artificial intelligence,Generative grammar,Stacking,Sketch
Conference
ISSN
ISBN
Citations 
1051-4651
978-1-5386-3789-0
1
PageRank 
References 
Authors
0.36
0
4
Name
Order
Citations
PageRank
Yu Liu119825.45
Yanming Guo212813.06
Wei Chen31711246.70
Michael S. Lew42742166.02