Results 11 to 20 of about 97,810,316 (272)

Unpaired Image-to-Image Translation with Diffusion Adversarial Network

Mathematics
Unpaired image translation with feature-level constraints presents significant challenges, including unstable network training and low diversity in generated tasks. This limitation is typically attributed to the following situations: 1.
Hangyao Tu, Zheng Wang, Yanwei Zhao
doaj   +3 more sources

Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation

IEEE Access
A common goal of unpaired image-to-image translation is to preserve content consistency between source images and translated images while mimicking the style of the target domain.
Bonifaz Stuhr, Jurgen Brauer, Bernhard Schick, Jordi Gonzalez   +3 more
doaj   +7 more sources

Random Reconstructed Unpaired Image-to-Image Translation

IEEE Transactions on Industrial Informatics, 2023
The goal of unpaired image-to-image translation is to learn a mapping from a source domain to a target domain without using any labeled examples of paired images. This problem can be solved by learning the conditional distribution of source images in the
Xiaoqin Zhang, Chenxiang Fan, Zhiheng Xiao, Li Zhao, Huiling Chen, Xiaojun Chang   +5 more
openaire   +2 more sources

Implicit pairs for boosting unpaired image-to-image translation

Visual Informatics, 2020
In image-to-image translation the goal is to learn a mapping from one image domain to another. In the case of supervised approaches the mapping is learned from paired samples.
Yiftach Ginger, Dov Danon, Hadar Averbuch-Elor, Daniel Cohen-Or   +3 more
doaj   +3 more sources

SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation

Proceedings of the AAAI Conference on Artificial Intelligence, 2023
We propose a novel solution for unpaired image-to-image (I2I) translation. To translate complex images with a wide range of objects to a different domain, recent approaches often use the object annotations to perform per-class source-to-target style mapping. However, there remains a point for us to exploit in the I2I.
Seokbeom Song, Suhyeon Lee 0002, Hongje Seong, Kyoungwon Min, Euntai Kim   +4 more
core   +5 more sources

Unpaired Image-to-Image Translation with Shortest Path Regularization

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Unpaired image-to-image translation aims to learn proper mappings that can map images from one domain to another domain while preserving the content of the input image. However, with large enough capacities, the network can learn to map the inputs to any
Shaoan Xie, Yanwu Xu 0003, Mingming Gong, Kun Zhang 0001   +3 more
openaire   +3 more sources

Unpaired Image-to-Image Translation to Improve Log End Identification

ESANN 2024 proceesdings
Visual re-identification tasks are often subject to large domain variations due to camera types, brightness conditions, or environmental differences. For identification models to generalize in such varying domains, a large amount of training data is necessary for capturing these variations.
Björnberg, Dag, Ericsson, Morgan, Löwe, Welf, Nordqvist, Jonas   +3 more
core   +7 more sources

Unpaired Image-To-Image Shape Translation Across Fashion Data

2020 IEEE International Conference on Image Processing (ICIP), 2020
We address the problem of unpaired geometric image-to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object while preserving its appearance. Our model is trained without the need for paired images.
Kaili Wang, Liqian Ma, José Oramas M., Luc Van Gool, Tinne Tuytelaars   +4 more
openaire   +3 more sources

Multi-feature contrastive learning for unpaired image-to-image translation

Complex & Intelligent Systems, 2022
Unpaired image-to-image translation for the generation field has made much progress recently. However, these methods suffer from mode collapse because of the overfitting of the discriminator.
Yao Gou, Min Li, Yu Song, Yujie He, Litao Wang   +4 more
doaj   +2 more sources

Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation

Proceedings of the 30th ACM International Conference on Multimedia, 2022
Unpaired image-to-image translation aims to find a mapping between the source domain and the target domain. To alleviate the problem of the lack of supervised labels for the source images, cycle-consistency based methods have been proposed for image structure preservation by assuming a reversible relationship between unpaired images.
Yupei Lin, Sen Zhang 0006, Tianshui Chen, Yongyi Lu, Guangping Li 0002, Yukai Shi   +5 more
openaire   +4 more sources