Fast Image Processing with Fully-Convolutional Networks

@article{Chen2017FastIP,
  title={Fast Image Processing with Fully-Convolutional Networks},
  author={Qifeng Chen and J. Xu and V. Koltun},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={2516-2525}
}
We present an approach to accelerating a wide variety of image processing operators. [...] Key Result We show that our models general- ize across datasets and across resolutions, and investigate a number of extensions of the presented approach.Expand
162 Citations
Learned perceptual image enhancement
  • 41
  • Highly Influenced
  • PDF
Evaluating Parameterization Methods for Convolutional Neural Network (CNN)-Based Image Operators
  • 2
  • PDF
Image smoothing via unsupervised learning
  • 42
  • PDF
CNN Based Image Restoration
  • 3
Decouple Learning for Parameterized Image Operators
  • 27
  • Highly Influenced
  • PDF
Spatially Variant Linear Representation Models for Joint Filtering
  • 12
  • PDF
Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
  • 23
  • PDF
Controllable Image Processing via Adaptive FilterBank Pyramid
  • 2
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 92 REFERENCES
Natural Image Denoising with Convolutional Networks
  • 632
  • PDF
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
  • 4,327
  • Highly Influential
  • PDF
Image Super-Resolution Using Deep Convolutional Networks
  • 3,629
  • PDF
On learning optimized reaction diffusion processes for effective image restoration
  • 236
  • PDF
Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 47,498
  • PDF
Bilateral guided upsampling
  • 43
  • Highly Influential
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
  • 2,819
  • PDF
Deep Convolutional Neural Network for Image Deconvolution
  • 574
  • PDF
U-Net: Convolutional Networks for Biomedical Image Segmentation
  • 20,926
  • PDF
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 4,656
  • PDF
...
1
2
3
4
5
...