Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

TediGAN: Text-Guided Diverse Face Image Generation and Manipulation

About

In this work, we propose TediGAN, a novel framework for multi-modal image generation and manipulation with textual descriptions. The proposed method consists of three components: StyleGAN inversion module, visual-linguistic similarity learning, and instance-level optimization. The inversion module maps real images to the latent space of a well-trained StyleGAN. The visual-linguistic similarity learns the text-image matching by mapping the image and text into a common embedding space. The instance-level optimization is for identity preservation in manipulation. Our model can produce diverse and high-quality images with an unprecedented resolution at 1024. Using a control mechanism based on style-mixing, our TediGAN inherently supports image synthesis with multi-modal inputs, such as sketches or semantic labels, with or without instance guidance. To facilitate text-guided multi-modal synthesis, we propose the Multi-Modal CelebA-HQ, a large-scale dataset consisting of real face images and corresponding semantic segmentation map, sketch, and textual descriptions. Extensive experiments on the introduced dataset demonstrate the superior performance of our proposed method. Code and data are available at https://github.com/weihaox/TediGAN.

Weihao Xia, Yujiu Yang, Jing-Hao Xue, Baoyuan Wu• 2020

Related benchmarks

TaskDatasetResultRank
Text-to-Image SynthesisCelebA-HQ (test)
FID16.45
19
Text-to-Image GenerationMulti-modal CelebA-HQ
FID106.4
19
Facial Image GenerationDISFA
FID7.054
11
Facial Image GenerationBP4D
FID7.321
11
Semantic to Face GenerationCelebA
FID69.51
10
Semantic Label to Face GenerationFFHQ
FID125.3
10
Text-driven Image ManipulationCelebA-HQ (test)
Accuracy1.5
10
Text-driven Image ManipulationFFHQ (test)
FID31.13
9
Text-to-Image SynthesisCUB unseen bird species
Accuracy6.3
8
Text-to-Image SynthesisMM-CelebA-HQ 256x256
FID106.4
7
Showing 10 of 16 rows

Other info

Code

Follow for update