Amortised MAP Inference for Image Super-resolution

@article{Snderby2016AmortisedMI,
  title={Amortised MAP Inference for Image Super-resolution},
  author={Casper Kaae S\onderby and Jose Caballero and Lucas Theis and Wenzhe Shi and Ferenc Husz{\'a}r},
  journal={CoRR},
  year={2016},
  volume={abs/1610.04490}
}
Image Super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often with a pixel-wise mean squared error (MSE) loss. However, the outputs from such methods tend to be blurry, over-smoothed and generally appear implausible. A more desirable approach would employ Maximum a Posteriori (MAP) inference, preferring solutions that… CONTINUE READING
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 176 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 147 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 119 extracted citations

Emergence of Invariance and Disentanglement in Deep Representations

2018 Information Theory and Applications Workshop (ITA) • 2018
View 13 Excerpts
Highly Influenced

Adversarial Message Passing For Graphical Models

ArXiv • 2016
View 4 Excerpts
Highly Influenced

On the convergence properties of GAN training

ArXiv • 2018
View 4 Excerpts
Highly Influenced

177 Citations

0501002016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 177 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 40 references

Improved Techniques for Training GANs

NIPS • 2016
View 5 Excerpts
Highly Influenced

Open source code

David Garcia
Sept 2016, • 2016
View 4 Excerpts
Highly Influenced

Image Super-Resolution Using Deep Convolutional Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2016
View 4 Excerpts
Highly Influenced

Generative Adversarial Nets

View 3 Excerpts
Highly Influenced

Densely Connected Convolutional Networks

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 1 Excerpt

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 4 Excerpts

An alternative update rule for generative adversarial networks

Ferenc Huszár
Unpublished note (retrieved on 7 Oct 2016), • 2016
View 1 Excerpt

Similar Papers

Loading similar papers…