Viet-Anh on Software Logo

What is: pixel2style2pixel?

SourceEncoding in Style: a StyleGAN Encoder for Image-to-Image Translation
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Pixel2Style2Pixel, or pSp, is an image-to-image translation framework that is based on a novel encoder that directly generates a series of style vectors which are fed into a pretrained StyleGAN generator, forming the extended W+\mathcal{W+} latent space. Feature maps are first extracted using a standard feature pyramid over a ResNet backbone. Then, for each of 1818 target styles, a small mapping network is trained to extract the learned styles from the corresponding feature map, where styles (02)(0-2) are generated from the small feature map, (36)(3-6) from the medium feature map, and (718)(7-18) from the largest feature map. The mapping network, map2style, is a small fully convolutional network, which gradually reduces spatial size using a set of 2-strided convolutions followed by LeakyReLU activations. Each generated 512 vector, is fed into StyleGAN, starting from its matching affine transformation, AA.