Super resolution is the task of taking an input of a low resolution (LR) and upscaling it to that of a high resolution.
( Credit: MemNet )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
#3 best model for Image Super-Resolution on VggFace2 - 8x upscaling
We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
#2 best model for Video Super-Resolution on Xiph HD - 4x upscaling
This means that the super-resolution (SR) operation is performed in HR space.
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN).
#10 best model for Image Super-Resolution on Urban100 - 2x upscaling
To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).
#2 best model for Image Super-Resolution on PIRM-test
In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning.
We present a novel super-resolution algorithm addressing this problem, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature.
Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution.
In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers.
#9 best model for Image Super-Resolution on Manga109 - 4x upscaling