CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation

doi:doi:10.57702/2w6l3p6j

CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation

Generating photo-realistic images from a text description is a challenging problem in computer vision. Previ- ous works have shown promising performance to generate synthetic images conditional on text by Generative Adver- sarial Networks (GANs). In this paper, we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic images.

BibTex:

@dataset{Tao_Hu_and_Chengjiang_Long_and_Chunxia_Xiao_2024,
    abstract = {Generating photo-realistic images from a text description is a challenging problem in computer vision. Previ- ous works have shown promising performance to generate synthetic images conditional on text by Generative Adver-  sarial Networks (GANs). In this paper, we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic images.},
    author = {Tao Hu and Chengjiang Long and Chunxia Xiao},
    doi = {10.57702/2w6l3p6j},
    institution = {No Organization},
    keyword = {'Category-Consistent', 'Computer Vision', 'GANs', 'Relativistic Diverse', 'Text-to-Image Generation'},
    month = {dec},
    publisher = {TIB},
    title = {CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation},
    url = {https://service.tib.eu/ldmservice/dataset/crd-cgan--category-consistent-and-relativistic-constraints-for-diverse-text-to-image-generation},
    year = {2024}
}