Unlike previous integral gradient methods, our FAIG aims at finding the most discriminative filters instead of input pixels/features for degradation removal in blind SR networks.
Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images.
However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e. g. scale and rotation) and the resolution gap (e. g. HR and LR).
Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.
Ranked #1 on Blind Face Restoration on CelebA-Test
In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators.
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension.
We show that pre-trained Generative Adversarial Networks (GANs), e. g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR).
Aside from the contributions to deformable alignment, our formulation inspires a more flexible approach to introduce offset diversity to flow-based alignment, improving its performance.
To leverage this, we propose Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region.
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 it is possible to recover textures faithful to semantic classes.
Ranked #49 on Image Super-Resolution on BSD100 - 4x upscaling