• Corpus ID: 244708918

ManiFest: Manifold Deformation for Few-shot Image Translation

@article{Pizzati2021ManiFestMD,
  title={ManiFest: Manifold Deformation for Few-shot Image Translation},
  author={Fabio Pizzati and Jean-François Lalonde and Raoul de Charette},
  journal={ArXiv},
  year={2021},
  volume={abs/2111.13681}
}
Most image-to-image translation methods require a large number of training images, which restricts their applicability. We instead propose ManiFest: a framework for few-shot image translation that learns a context-aware representation of a target domain from a few images only. To enforce feature consistency, our framework learns a style manifold between source and proxy anchor domains (assumed to be composed of large numbers of images). The learned manifold is interpolated and deformed towards… 
Physics-informed Guided Disentanglement in Generative Networks
TLDR
This paper builds upon collection of simple physics models and presents a comprehensive method for disentangling visual traits in target images, guiding the process with a physical model that renders some of the target traits, and learning the remaining ones.
Attribute Group Editing for Reliable Few-shot Image Generation
TLDR
A new “editing-based” method, i.e., Attribute Group Editing (AGE), for few-shot image generation, capable of not only producing more realistic and diverse images for downstream visual applications with limited data but achieving controllable image editing with interpretable category-irrelevant directions.

References

SHOWING 1-10 OF 69 REFERENCES
Few-Shot Unsupervised Image-to-Image Translation
TLDR
This model achieves this few-shot generation capability by coupling an adversarial training scheme with a novel network design, and verifies the effectiveness of the proposed framework through extensive experimental validation and comparisons to several baseline methods on benchmark datasets.
COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
TLDR
A new few-shot image translation model, COCO-FUNIT, is proposed, which computes the style embedding of the example images conditioned on the input image and a new module called the constant style bias, which shows effectiveness in addressing the content loss problem.
Semi-Supervised Learning for Few-Shot Image-to-Image Translation
TLDR
This work proposes applying semi-supervised learning via a noise-tolerant pseudo-labeling procedure, and applies a cycle consistency constraint to further exploit the information from unlabeled images, either from the same dataset or external.
InstaGAN: Instance-aware Image-to-Image Translation
TLDR
A novel method is proposed, coined instance-aware GAN (InstaGAN), that incorporates the instance information and improves multi-instance transfiguration and introduces a context preserving loss that encourages the network to learn the identity function outside of target instances.
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.
Contrastive Learning for Unpaired Image-to-Image Translation
TLDR
The framework enables one-sided translation in the unpaired image-to-image translation setting, while improving quality and reducing training time, and can be extended to the training setting where each "domain" is only a single image.
Multimodal Structure-Consistent Image-to-Image Translation
TLDR
This work introduces cycle-structure consistency for generating diverse and structure-preserved translated images across complex domains, such as between day and night, for object detector training and demonstrates that this model achieves significant improvement and outperforms other methods on the detection accuracies and the FCN scores.
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.
Few-shot Image Generation via Cross-domain Correspondence
TLDR
This work seeks to utilize a large source domain for pretraining and transfer the diversity information from source to target and proposes to preserve the relative similarities and differences between instances in the source via a novel cross-domain distance consistency loss.
...
1
2
3
4
5
...