TextFace: Text-to-Style Mapping Based Face Generation and Manipulation
- 17 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 3409-3419
Abstract
As a sub-topic of Text-to-Image synthesis, Text-to-Face generation has a great potential in face related applications. In this paper, we propose a generic Text-to-Face framework, namely TextFace, to achieve diverse and high-quality face image generation from text description. We introduce a novel method called Text-to-Style mapping, where the text description can be directly encoded into the latent space of a pretrained StyleGAN. Guided by our text-image similarity matching and face captioning based text alignment, the textual latent code can be fed into a well-trained StyleGAN's generator, to produce diverse face images with high resolution (1024 1024). Furthermore, our model inherently supports the semantic face editing using text descriptions. Finally, experimental results quantitatively and qualitatively demonstrate the superior performance of our model.Keywords
Funding Information
- National Natural Science Foundation of China (91959108)
- Basic and Applied Basic Research Foundation of Guangdong Province (2020A1515111199)
This publication has 43 references indexed in Scilit:
- Semantic Image Synthesis via Adversarial Learning2017
- Generative Visual Manipulation on the Natural Image Manifold2016
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- FaceNet: A unified embedding for face recognition and clustering2015
- Deep visual-semantic alignments for generating image descriptions2015
- Show and tell: A neural image caption generator2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997
- Long Short-Term MemoryNeural Computation, 1997