Pseudo-Supervised Learning for Semantic Multi-Style Transfer
Numerous methods for style transfer have been developed using unsupervised learning and gained impressive results. However, optimal style transfer cannot be conducted from a global fashion in certain style domains, mainly when a single target-style domain contains semantic objects that have their ow...
Main Authors: | Saehun Kim, Jeonghyeok Do, Munchurl Kim |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9316188/ |
Similar Items
-
Unsupervised Transformation Network Based on GANs for Target-Domain Oriented Image Translation
by: Hongwei Ge, et al.
Published: (2018-01-01) -
Unsupervised Exemplar-Domain Aware Image-to-Image Translation
by: Yuanbin Fu, et al.
Published: (2021-05-01) -
UGAN: Unified Generative Adversarial Networks for Multidirectional Text Style Transfer
by: Wei Yu, et al.
Published: (2020-01-01) -
Sparse GANs for Thermal Infrared Image Generation From Optical Image
by: Xiaoyan Qian, et al.
Published: (2020-01-01) -
Supervised Video-to-Video Synthesis for Single Human Pose Transfer
by: Hongyu Wang, et al.
Published: (2021-01-01)