Since features in the codebook have shown the ability to generate natural textures in the pretrain stage, QuanTexSR can generate rich and realistic textures with the pretrained codebook as texture priors.
We introduce rectification blocks to rectify features extracted by a state-of-the-art recognition model, in both spatial and channel dimensions, to minimize the distance between a masked face and its mask-free counterpart in the rectified feature space.
Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction.
Visualization of the attention maps shows that our spatial attention network can capture the key face structures well even for very low resolution faces (e. g., $16\times16$).
Compared with previous networks, the proposed PSFR-GAN makes full use of the semantic (parsing maps) and pixel (LQ images) space information from different scales of input pairs.
Ranked #3 on Blind Face Restoration on CelebA-Test
We utilize a fully convolutional neural network (FCNN) to create the content image, and propose a style transfer approach to introduce textures and shadings based on a newly proposed pyramid column feature.
Next, with the degraded input, we match and select the most similar component features from their corresponding dictionaries and transfer the high-quality details to the input via the proposed dictionary feature transfer (DFT) block.
We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales.
Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.
Ranked #1 on Face Sketch Synthesis on CUHK
Unlike previous work which employed a global spatial transformer network to rectify the entire distorted text image, we take an approach of detecting and rectifying individual characters.