Image2StyleGAN++: How to Edit the Embedded Images?
Top Cited Papers
- 1 June 2020
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8293-8302
- https://doi.org/10.1109/cvpr42600.2020.00832
Abstract
We propose Image2StyleGAN++, a flexible image editing framework with many applications. Our framework extends the recent Image2StyleGAN in three ways. First, we introduce noise optimization as a complement to the W+ latent space embedding. Our noise optimization can restore high frequency features in images and thus significantly improves the quality of reconstructed images, e.g. a big increase of PSNR from 20 dB to 45 dB. Second, we extend the global W+ latent space embedding to enable local embeddings. Third, we combine embedding with activation tensor manipulation to perform high quality local edits along with global semantic edits on images. Such edits motivate various high quality image editing applications, e.g. image reconstruction, image inpainting, image crossover, local style transfer, image editing using scribbles, and attribute level feature transfer. Examples of the edited images are shown across the paper for visual inspection.Keywords
This publication has 16 references indexed in Scilit:
- TextureGAN: Controlling Deep Image Synthesis with Texture PatchesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Generative Image Inpainting with Contextual AttentionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Least Squares Generative Adversarial NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Controlling Perceptual Factors in Neural Style TransferPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Perceptual Generative Adversarial Networks for Small Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Image-to-Image Translation with Conditional Adversarial NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Image Style Transfer Using Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial NetworksPublished by Springer Science and Business Media LLC ,2016
- Generative Visual Manipulation on the Natural Image ManifoldPublished by Springer Science and Business Media LLC ,2016
- ImageNet: A large-scale hierarchical image databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009