A Synergy of Computer Graphics and Generative AI: Advancements and Challenges

Abstract

A traditional computer graphics domain has received an unprecedented boost from the newest developments in generative Artificial Intelligence (GenAI). It affects all areas: from image generation, to face recognition, to object detection, to aerial surveillance, to autonomous car vision systems. The newest deep learning architectures make it possible to generate new images from texts, to apply styles to portraits, to de-identify facial images, and to recognize human and objects in videos. This keynote will delve into some of the most exciting applications in medical AI diagnostics, human face recognition and aesthetics domains, while making a strong case for resulting image authenticity, bias mitigation, and trust.