English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we are dedicated to text-guided image generation and propose anovel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The keyidea of our CLIP2GAN is to bridge the output feature embedding space of CLIPand the input latent space of StyleGAN, which is realized by introducing amapping network. In the training stage, we encode an image with CLIP and mapthe output feature to a latent code, which is further used to reconstruct theimage. In this way, the mapping network is optimized in a self-supervisedlearning way. In the inference stage, since CLIP can embed both image and textinto a shared feature embedding space, we replace CLIP image encoder in thetraining architecture with CLIP text encoder, while keeping the followingmapping network as well as StyleGAN model. As a result, we can flexibly input atext description to generate an image. Moreover, by simply adding mapped textfeatures of an attribute to a mapped CLIP image feature, we can effectivelyedit the attribute to the image. Extensive experiments demonstrate the superiorperformance of our proposed CLIP2GAN compared to previous methods.

CLIP2GAN: Towards Bridging Text with the Latent Space of GANs