Generative Adversarial Networks

PSFR-GAN is a semantic-aware style transformation framework for face restoration. Given a pair of LQ face image and its corresponding parsing map, we first generate a multi-scale pyramid of the inputs, and then progressively modulate different scale features from coarse-to-fine in a semantic-aware style transfer way. 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 inputs.

Source: Progressive Semantic-Aware Style Transformation for Blind Face Restoration

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Blind Face Restoration 1 25.00%
Face Parsing 1 25.00%
Semantic Parsing 1 25.00%
Style Transfer 1 25.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories