Presentation

· Contributors · Organizations · Search Program · My Schedule · Happening Now

A Hybrid Generator Architecture for Controllable Face Synthesis

DescriptionThis research presents a data-driven generator architecture that combines the photorealistic qualities of GANs with disentangled controls and 3D mesh manipulation. This approach enables precise control and interpretability without the need for labeled training data, ensuring compatibility with traditional animation tools, and promoting greater flexibility and creativity.

Authors