Diversified realistic face image generation GAN for human subjects in multimedia content creation

• Published in: Computer animation and virtual worlds Vol. 35; no. 2
• Main Authors: Kumar, Lalit, Singh, Dushyant Kumar
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.03.2024; Wiley Subscription Services, Inc
• Subjects: deep learning; face image generation; Generative Adversarial Network; Image enhancement; image generation; Image processing; Multimedia; ResNet‐50; VGG‐16
• ISSN: 1546-4261; 1546-427X
• DOI: 10.1002/cav.2232

Face image generation plays an important role in generating innovative and unique multimedia content using the GAN model. With these qualities of the GAN model, they have numerous challenges in the human face image generation. The problems encountered in the generation of facial images are like blurriness in images, incomplete details in the generated facial images, high computational power requirements, and so forth. In this manuscript, we proposed a GAN model that utilizes the composite strength of VGG‐16 and ResNet‐50's models to overcome those difficulties. It uses VGG‐16 to build a discriminator model to discriminate between real and fake images. The generator model utilizes a combination of components from the ResNet‐50 and VGG‐16 models to enhance the image generation process at each iteration, resulting in the creation of realistic face images. The proposed DRFI GAN (Diversified and Realistic Face Image Generation GAN) model's generator achieves an impressive low FID score of 20.50, which is less than existing state‐of‐the‐art approaches. Furthermore, our findings indicate that the images generated by the DRFI GAN model exhibit 10%–15% greater efficiency and realism with reduced training time compared to existing state‐of‐the‐art methods with lower FID scores. DRFIGAN, or Diverse and Realistic Face Image Generation Generative Adversarial Network, is an advanced model utilizing VGG‐16 and ResNet‐50 architectures togenerate high‐quality face images. The generator integrates features fromVGG‐16 and ResNet‐50, leveraging their abilities to capture detailed andcomplex features for realistic and diverse outputs. Meanwhile, the discriminator employs VGG‐16 to authenticate generated images based onhigh‐level feature representations, ensuring authenticity. By combining these architectures, DRFI GAN achieves superior performance in producing visually compelling face images with remarkable realism.