• Corpus ID: 239998706

Separating Content and Style for Unsupervised Image-to-Image Translation

@article{Liu2021SeparatingCA,
  title={Separating Content and Style for Unsupervised Image-to-Image Translation},
  author={Yunfei Liu and Haofei Wang and Yang Yue and Feng Lu},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.14404}
}
Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples. Existing works focus on disentangling domaininvariant content code and domain-specific style code individually for multimodal purposes. However, less attention has been paid to interpreting and manipulating the translated image. In this paper, we propose to separate the content code and style code simultaneously in a unified framework. Based on the correlation between the latent… 

References

SHOWING 1-10 OF 63 REFERENCES
Improving Style-Content Disentanglement in Image-to-Image Translation
TLDR
This work proposes a principled approach for improving style-content disentanglement in image-to-image translation by considering the information flow into each of the representations, and introduces an additional loss term which serves as a content-bottleneck.
Unsupervised Image-to-Image Translation Networks
TLDR
This work makes a shared-latent space assumption and proposes an unsupervised image-to-image translation framework based on Coupled GANs that achieves state-of-the-art performance on benchmark datasets.
Multimodal Unsupervised Image-to-Image Translation
TLDR
A Multimodal Unsupervised Image-to-image Translation (MUNIT) framework that assumes that the image representation can be decomposed into a content code that is domain-invariant, and a style code that captures domain-specific properties.
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
TLDR
The Exemplar Guided & Semantically Consistent Image-to-image Translation (EGSC-IT) network is proposed which conditions the translation process on an exemplar image in the target domain and introduces the concept of feature masks that provide coarse semantic guidance without requiring the use of any semantic labels.
Towards Instance-Level Image-To-Image Translation
TLDR
This paper presents a simple yet effective instance-aware image-to-image translation approach (INIT), which employs the fine-grained local (instance) and global styles to the target image spatially and collects a large-scale benchmark for the new instance-level translation task.
Diverse Image-to-Image Translation via Disentangled Representations
TLDR
This work presents an approach based on disentangled representation for producing diverse outputs without paired training images, and proposes to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and adomain-specific attribute space.
MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation
TLDR
This work designs MILO (Mutual Information LOss), a new stochastically-defined loss function based on information theory that reflects the interpretation of latent variables as a random variable in multimodal translation models.
Controlling biases and diversity in diverse image-to-image translation
TLDR
This paper proposes the use of semantic constraints that enforce the preservation of desired image properties in image-to-image translation, and results in less unwanted changes in the translated images while still performing the wanted transformation.
TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation
TLDR
A novel disentangle-and-translate framework to tackle the complex objects image-to-image translation task, which disentangles image space into a Cartesian product of the appearance and the geometry latent spaces and supports multimodal translation.
Show, Attend, and Translate: Unsupervised Image Translation With Self-Regularization and Attention
TLDR
This work constrain the problem with the assumption that the translated image needs to be perceptually similar to the original image and also appears to be drawn from the new domain, and proposes a simple yet effective image translation model consisting of a single generator trained with a self-regularization term and an adversarial term.
...
1
2
3
4
5
...