To address the problems of inconsistency between generated images and text descriptions and low image resolution in text-generated face methods, this paper proposes a cross-modal text-generated face image network framework. Firstly, the CLIP pre-training model is adopted to extract features from the text, and the text semantic features are enhanced by the conditional enhancement module to generate hidden vectors; then the hidden vector is projected into the implicit space of the pre-trained model StyleGAN by the mapping network to obtain the untangled hidden vector, which is input to the StyleGAN generator to generate high-resolution face images; finally, the text reconstruction module is adopted to regenerate the face images into text, and the semantic alignment loss between the reconstructed text and the input text is calculated and utilized as semantic supervision to guide the network training. The training and testing are performed on two datasets, Multi-Modal CelebA-HQ and CelebAText-HQ, and the experimental results show that compared with other methods, the method in this paper can generate high-resolution face images that are more consistent with the text description.
ZHANGH, XUT, LIH, et al.Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision,2017: 5907-5915.
[2]
ZHANGH, XUT, LIH, et al.Stackgan++: realistic image synthesis with stacked generative adversarial networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2018, 41(8): 1947-1962.
[3]
XUT, ZHANGP, HUANGQ, et al.Attngan: fine-grained text to image generation with attentional generative adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1316-1324.
[4]
QIAOT, ZHANGJ, XUD, et al.Mirrorgan: learning text-to-image generation by redescription[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 1505-1514.
[5]
TAOM, TANGH, WUF, et al.Df-gan: a simple and effective baseline for text-to-image synthsis[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 16515-16525.
[6]
KARRAST, LAINES, AILAT.A style-based generator architecture for generative adversarial networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2019: 4401-4410.
[7]
RADFORDA, KIMJ W, HALLACYC, et al.Learning transferable visual models from natural language supervision[C]//International Conference on Machine Learning, PMLR, 2021: 8748-8763.
[8]
ZHOUP, SHIW, TIANJ, et al.Attention-based bidirectional long short-term memory networks for relation classification[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016(2): 207-212.
[9]
LEDIGC, THEISL, HUSZÁRF, et al.Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4681-4690.
[10]
ZHUM, PANP, CHENW, et al.Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 5802-5810.
[11]
XIAW, YANGY, XUEJ H, et al.Tedigan: Text-guided diverse face image generation and manipulation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 2256-2265.