Super-Resolution paper
Super-resolution imaging (SR) is a class of techniques that enhance (increase) the resolution of an imaging system. In optical SR the diffraction limit of systems is transcended, while in geometrical SR the resolution of digital imaging sensors is enhanced.
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
JPEG Artifact Correction JPEG Artifact Correction
Correction of visual artifacts caused by JPEG compression, these artifacts are usually grouped into three types: blocking, blurring, and ringing. They are caused by quantization and removal of high frequency DCT coefficients.
JPEG Artifact Correction
Correction of visual artifacts caused by JPEG compression, these artifacts are usually grouped into three types: blocking, blurring, and ringing. They are caused by quantization and removal of high frequency DCT coefficients.
Image restoration
Image restoration is the operation of taking a corrupt/noisy image and estimating the clean, original image. Corruption may come in many forms such as motion blur, noise and camera mis-focus.Image restoration is performed by reversing the process that blurred the image and such is performed by imaging a point source.
Denoising
Denoising is the process of removing noise from a signal. Noise reduction techniques exist for audio and images. Noise reduction algorithms may distort the signal to some degree.
Denoising
Denoising is the process of removing noise from a signal. Noise reduction techniques exist for audio and images. Noise reduction algorithms may distort the signal to some degree.
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
We propose an alternative formulation of the super-resolution problem based on creating realistic SR images that downscale correctly. We present an algorithm addressing this problem, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature.
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
We propose an alternative formulation of the super-resolution problem based on creating realistic SR images that downscale correctly. We present an algorithm addressing this problem, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature.
Deep Back-Projection Networks For Super-Resolution
We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components.
March 7, 2018
Deep Back-Projection Networks For Super-Resolution
We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts.
September 1, 2018
Video Super-Resolution
Video Super-Resolution (VSR) is the process of generating high-resolution video frames from the given low-resolution ones. Unlike single image super-resolution (SISR), the main goal is not only to restore more fine details while saving coarse ones, but also to preserve motion consistensy.There are many approaches for this task.
Image Super-Resolution
In this task, we try to upsample the image and create a high-resolution image with help of a low-resolution image. The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error.
Face Hallucination Face Hallucination
Face hallucination is the task of generating high-resolution (HR) facial images from low-resolution (LR) inputs.
Face Hallucination
Face hallucination is the task of generating high-resolution (HR) facial images from low-resolution (LR) inputs.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts.
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output.
September 16, 2016
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output.