• However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technologies to a bigger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Our important insight is to take advantage of the powerful vision-language model CLIP for supervising…[Read more]

  • Santana Dodson became a registered member 2 years, 3 months ago