Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression

  title={Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression},
  author={A. Murat Tekalp and Michele Covell and Radu Timofte and Chao Dong},
T HE huge success of deep-learning–based approaches in computer vision has inspired research in learned solutions to classic image/video processing problems, such as denoising, deblurring, dehazing, deraining, super-resolution (SR), and compression. Hence, learning-based methods have emerged as a promising nonlinear signal-processing framework for image/video restoration and compression. Recent works have shown that learned models can achieve significant performance gains, especially in terms… Expand
An Innovative Approach for Denoising of the Digital Video Stream
An efficient video Denoising framework is disclosed that takes the noisy video signal in the form of frames per second and performs the video denoising using shot detection, compensation, intensity calculations, and motion estimation process. Expand


A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
A CNN-based post-processing algorithm for High Efficiency Video Coding (HEVC), the state-of-the-art video coding standard, that outperforms previously studied networks in achieving higher bit-rate reduction, lower memory cost, and multiplied computational speedup. Expand
DVC: An End-To-End Deep Video Compression Framework
This paper proposes the first end-to-end video compression deep model that jointly optimizes all the components for video compression, and shows that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard MS-SSIM. Expand
Interpreting CNN For Low Complexity Learned Sub-Pixel Motion Compensation In Video Coding
A novel neural network-based tool is presented which improves the interpolation of reference samples needed for fractional precision motion compensation by focusing on complexity reduction achieved by interpreting the interpolations filters learned by the networks. Expand
Scale-Space Flow for End-to-End Optimized Video Compression
This paper proposes scale-space flow, an intuitive generalization of optical flow that adds a scale parameter to allow the network to better model uncertainty and outperform analogous state-of-the art learned video compression models while being trained using a much simpler procedure and without any pre-trained optical flow networks. Expand
Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks
This work proposes a Cycle-in-Cycle network structure with generative adversarial networks (GAN) as the basic component to tackle the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Expand
Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
The proposed depth guided degradation model learning-based image super-resolution (DGDML-SR) achieves visually pleasing results and can outperform the state-of-the-arts in perceptual metrics. Expand
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Extensive experimental results show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications. Expand
Variational image compression with a scale hyperprior
It is demonstrated that this model leads to state-of-the-art image compression when measuring visual quality using the popular MS-SSIM index, and yields rate-distortion performance surpassing published ANN-based methods when evaluated using a more traditional metric based on squared error (PSNR). Expand
"Zero-Shot" Super-Resolution Using Deep Internal Learning
This paper exploits the internal recurrence of information inside a single image, and train a small image-specific CNN at test time, on examples extracted solely from the input image itself, which is the first unsupervised CNN-based SR method. Expand
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
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss. Expand