Typically, blind face restoration will use facial priors such as geometry and reference. However, these aren't particularly useful when the quality of input is low because it doesn't offer accurate geometric prior or when high-quality references are inaccessible, so they can only be applied in real-world scenarios to a limited extent. Researchers from Tencent AI propose their new GFP-GAN model to achieve a good balance of realness and fidelity in only one forward pass. The model consists of a degradation removal module and pretrained face generator as prior. They are connected by direct latent code mapping into coarse-to-fine channels using CS SFT layers.
GFPGAN is a blind face restoration algorithm towards real-world face images. Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity.
This post has been republished via RSS; it originally appeared at: Microsoft Research. The amount of visual data we accumulate around the world is mind boggling. However, not all the images are captured by high-end DSLR cameras, and very often they suffer from imperfections. It is of tremendous benefit to save those degraded images so that users can reuse them for their own design or other aesthetic purposes. In this blog, we are going to present our latest efforts in image enhancement.
The amount of visual data we accumulate around the world is mind boggling. However, not all the images are captured by high-end DSLR cameras, and very often they suffer from imperfections. It is of tremendous benefit to save those degraded images so that users can reuse them for their own design or other aesthetic purposes. In this blog, we are going to present our latest efforts in image enhancement. The first technique enhances the image resolution of an image file by referring to external reference images.
Super-resolution is a fundamental problem in computer vision which aims to overcome the spatial limitation of camera sensors. While significant progress has been made in single image super-resolution, most algorithms only perform well on synthetic data, which limits their applications in real scenarios. In this paper, we study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images. We focus on two issues of existing super-resolution algorithms: lack of realistic training data and insufficient utilization of visual information obtained from cameras. To address the first issue, we propose a method to generate more realistic training data by mimicking the imaging process of digital cameras. For the second issue, we develop a two-branch convolutional neural network to exploit the radiance information originally-recorded in raw images. In addition, we propose a dense channel-attention block for better image restoration as well as a learning-based guided filter network for effective color correction. Our model is able to generalize to different cameras without deliberately training on images from specific camera types. Extensive experiments demonstrate that the proposed algorithm can recover fine details and clear structures, and achieve high-quality results for single image super-resolution in real scenes.