SRMD - Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (CVPR, 2018)

  •        11

Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to deal with multiple degradations. To address these issues, we propose a dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the proposed super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images 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. In contrast to other CNN-based SISR methods which only take the LR image as input and lack scalability to handle other degradations, the proposed network takes the concatenated LR image and degradation maps as input, thus allowing a single model to manipulate multiple and even spatially variant degradations.

http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Learning_a_Single_CVPR_2018_paper.pdf
https://github.com/cszn/SRMD

Tags
Implementation
License
Platform

   




Related Projects

DnCNN - Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)

  •    Matlab

[demos] Demo_test_DnCNN-.m. [models] including the trained models for Gaussian denoising; a single model for Gaussian denoising, single image super-resolution (SISR) and deblocking.

caffe-vdsr - A Caffe-based implementation of very deep convolution network for image super-resolution

  •    Matlab

This is an implementation of "Accurate Image Super-Resolution Using Very Deep Convolutional Networks" (CVPR 2016 Oral Paper) in caffe. VDSR (Very Deep network for Super-Resolution) is an end-to-end network with 20 convolutional layers for single image super-resolution. The performance of VDSR is better than other state-of-the-art SISR methods, such as SRCNN, A+ and CSCN (My implementation of CSCN).

Image-Super-Resolution - Implementation of Super Resolution CNN in Keras.

  •    Python

Implementation of Image Super Resolution CNN in Keras from the paper Image Super-Resolution Using Deep Convolutional Networks. Also contains models that outperforms the above mentioned model, termed Expanded Super Resolution, Denoiseing Auto Encoder SRCNN which outperforms both of the above models and Deep Denoise SR, which with certain limitations, outperforms all of the above.

Accord.NET - Machine learning, Computer vision, Statistics and general scientific computing for .NET

  •    CSharp

The Accord.NET project provides machine learning, statistics, artificial intelligence, computer vision and image processing methods to .NET. It can be used on Microsoft Windows, Xamarin, Unity3D, Windows Store applications, Linux or mobile.

SelfExSR - Single Image Super-Resolution from Transformed Self-Exemplars (CVPR 2015)

  •    Matlab

The proposed algorithm achieves the state-of-the-art performance on image super-resolution without the need of any external training dataset, feature extraction and complicated learning algorithms. For more details, please visit our Project page. All the datasets (Set5, Set14, Urban 100, BSD 100, Sun-Hays 80), precomputed results and visual comparisons can be found in the following sections.


fashion-detection - Fashion Detection in the Wild (Deep Clothes Detector)

  •    Matlab

Deep Clothes Detector is a clothes detection framework based on Fast R-CNN. Given a fashion image, this software finds and localizes potential upper-body clothes, lower-body clothes and full-body clothes in it, respectively. Further information please contact Ziwei Liu.

clDNN - Compute Library for Deep Neural Networks (clDNN)

  •    C++

Compute Library for Deep Neural Networks (clDNN) is an open source performance library for Deep Learning (DL) applications intended for acceleration of DL Inference on Intel® Processor Graphics – including HD Graphics and Iris® Graphics. clDNN includes highly optimized building blocks for implementation of convolutional neural networks (CNN) with C and C++ interfaces. We created this project to enable the DL community to innovate on Intel® processors. Usages supported: Image recognition, image detection, and image segmentation.

Deep-Learning-with-Keras - Code repository for Deep Learning with Keras published by Packt

  •    Jupyter

This is the code repository for Deep Learning with Keras, published by Packt. It contains all the supporting project files necessary to work through the book from start to finish. This book starts by introducing you to supervised learning algorithms such as simple linear regression, classical multilayer perceptron, and more sophisticated Deep Convolutional Networks. In addition, you will also understand unsupervised learning algorithms such as Autoencoders, Restricted Boltzmann Machines, and Deep Belief Networks. Recurrent Networks and Long Short Term Memory (LSTM) networks are also explained in detail. You will also explore image processing involving the recognition of handwritten digital images, the classification of images into different categories, and advanced object recognition with related image annotations. An example of the identification of salient points for face detection is also provided.

waifu2x - Image Super-Resolution for Anime-Style Art

  •    Lua

Image Super-Resolution for Anime-style art using Deep Convolutional Neural Networks. And it supports photo. The demo application can be found at http://waifu2x.udp.jp/ .

food-101-keras - Food Classification with Deep Learning in Keras / Tensorflow

  •    Jupyter

If you are reading this on GitHub, the demo looks like this. Please follow the link below to view the live demo on my blog. Convolutional Neural Networks (CNN), a technique within the broader Deep Learning field, have been a revolutionary force in Computer Vision applications, especially in the past half-decade or so. One main use-case is that of image classification, e.g. determining whether a picture is that of a dog or cat.

Detectron - FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet

  •    Python

Detectron is Facebook AI Research's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework. At FAIR, Detectron has enabled numerous research projects, including: Feature Pyramid Networks for Object Detection, Mask R-CNN, Detecting and Recognizing Human-Object Interactions, Focal Loss for Dense Object Detection, Non-local Neural Networks, Learning to Segment Every Thing, and Data Distillation: Towards Omni-Supervised Learning.

one-pixel-attack-keras - Keras reimplementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

  •    Jupyter

How simple is it to cause a deep neural network to misclassify an image if an attacker is only allowed to modify the color of one pixel and only see the prediction probability? Turns out it is very simple. In many cases, an attacker can even cause the network to return any answer they want. The following project is a Keras reimplementation and tutorial of "One pixel attack for fooling deep neural networks".

MMLSpark - Microsoft Machine Learning for Apache Spark

  •    Scala

MMLSpark provides a number of deep learning and data science tools for Apache Spark, including seamless integration of Spark Machine Learning pipelines with Microsoft Cognitive Toolkit (CNTK) and OpenCV, enabling you to quickly create powerful, highly-scalable predictive and analytical models for large image and text datasets.MMLSpark requires Scala 2.11, Spark 2.1+, and either Python 2.7 or Python 3.5+. See the API documentation for Scala and for PySpark.

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

  •    Python

We run this script under TensorFlow 1.4 and the TensorLayer 1.8.0+. 🚀 This repo will be moved to here (please star) for life-cycle management soon. More cool Computer Vision applications such as pose estimation and style transfer can be found in this organization.

applied-deep-learning-resources - A collection of research articles, blog posts, slides and code snippets about deep learning in applied settings

  •    

A collection of research articles, blog posts, slides and code snippets about deep learning in applied settings. Including trained models and simple methods that can be used out of the box. Mainly focusing on Convolutional Neural Networks (CNN) but Recurrent Neural Networks (RNN), deep Q-Networks (DQN) and other interesting architectures will also be listed. ImageNet is the most important image classification and localization competition. Other data sets with results can be found from here: "Discover the current state of the art in objects classification." [link].

pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs

  •    Python

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic image-to-image translation. It can be used for turning semantic label maps into photo-realistic images or synthesizing portraits from face label maps. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs Ting-Chun Wang1, Ming-Yu Liu1, Jun-Yan Zhu2, Andrew Tao1, Jan Kautz1, Bryan Catanzaro1 1NVIDIA Corporation, 2UC Berkeley In arxiv, 2017.

Screenshot-to-code-in-Keras - A neural network that transforms a screenshot into a static website

  •    Jupyter

This is the code for the article 'Turning design mockups into code with deep learning' on FloydHub's blog. Within three years deep learning will change front-end development. It will increase prototyping speed and lower the barrier for building software.

All-About-the-GAN - All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN

  •    Python

The purpose of this repository is providing the curated list of the state-of-the-art works on the field of Generative Adversarial Networks since their introduction in 2014. You can also check out the same data in a tabular format with functionality to filter by year or do a quick search by title here.

PocketFlow - An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications

  •    Python

PocketFlow is an open-source framework for compressing and accelerating deep learning models with minimal human effort. Deep learning is widely used in various areas, such as computer vision, speech recognition, and natural language translation. However, deep learning models are often computational expensive, which limits further applications on mobile devices with limited computational resources. PocketFlow aims at providing an easy-to-use toolkit for developers to improve the inference efficiency with little or no performance degradation. Developers only needs to specify the desired compression and/or acceleration ratios and then PocketFlow will automatically choose proper hyper-parameters to generate a highly efficient compressed model for deployment.