Photo Style Transfer With Consistency Losses

@article{Yao2019PhotoST,
  title={Photo Style Transfer With Consistency Losses},
  author={X. Yao and G. Puy and P. P{\'e}rez},
  journal={2019 IEEE International Conference on Image Processing (ICIP)},
  year={2019},
  pages={2314-2318}
}
  • X. Yao, G. Puy, P. Pérez
  • Published 2019
  • Computer Science
  • 2019 IEEE International Conference on Image Processing (ICIP)
We address the problem of style transfer between two photos and propose a new way to preserve photorealism. Using the single pair of photos available as input, we train a pair of deep convolution networks (convnets), each of which transfers the style of one photo to the other. To enforce photorealism, we introduce a content preserving mechanism by combining a cycle-consistency loss with a self-consistency loss. Experimental results show that this method does not suffer from typical artifacts… Expand
1 Citations

Figures and Topics from this paper

Arbitrary Style Transfer Using Graph Instance Normalization

References

SHOWING 1-10 OF 24 REFERENCES
Deep Photo Style Transfer
Universal Style Transfer via Feature Transforms
A Flexible Convolutional Solver with Application to Photorealistic Style Transfer
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Image-to-Image Translation with Conditional Adversarial Networks
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
Structural inpainting
Image Style Transfer Using Convolutional Neural Networks
...
1
2
3
...