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.
Ranked #3 on Image Super-Resolution on WebFace - 8x upscaling
We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
Ranked #2 on Video Super-Resolution on Xiph HD - 4x upscaling
This means that the super-resolution (SR) operation is performed in HR space.
Ranked #1 on Video Super-Resolution on Xiph HD - 4x upscaling
We consider image transformation problems, where an input image is transformed into an output image.
Ranked #5 on Nuclear Segmentation on Cell17
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).
Ranked #2 on Face Hallucination on FFHQ 512 x 512 - 16x upscaling
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 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.
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.
Ranked #11 on Image Super-Resolution on BSD100 - 4x upscaling