Image-to-Image Translation with Conditional Adversarial Networks

@article{Isola2016ImagetoImageTW,
  title={Image-to-Image Translation with Conditional Adversarial Networks},
  author={Phillip Isola and Jun-Yan Zhu and Tinghui Zhou and Alexei A. Efros},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={5967-5976}
}
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 3,824 CITATIONS

Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation

VIEW 25 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Cantonese porcelain classification and image synthesis by ensemble learning and generative adversarial network

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Coarse-to-Fine Clothing Image Generation with Progressively Constructed Conditional GAN

VIEW 13 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Connecting Touch and Vision via Cross-Modal Prediction

VIEW 16 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS

Deep Single-Image Portrait Relighting

VIEW 14 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Differentiable surface splatting for point-based geometry processing

VIEW 14 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Discriminative Region Proposal Adversarial Network for High-Quality Image-to-Image Translation

VIEW 30 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Domain Adaptation of Landsat-8 and Proba-V Data Using Generative Adversarial Networks for Cloud Detection

VIEW 7 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 979 Highly Influenced Citations

  • Averaged 1,212 Citations per year from 2017 through 2019

  • 45% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 60 REFERENCES

Generative Adversarial Nets

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Context Encoders: Feature Learning by Inpainting

VIEW 5 EXCERPTS

Improved Techniques for Training GANs

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

kenter, rolf jagerman, and daan gosman. https://dekennisvannu.nl/site/artikel/ Help-ons-kunstmatige-intelligentie-testen/ 9163

  • Gerda bosman, tom
  • Accessed: 2017-08-31
  • 2017