I am a research scientist at VISUAL MEDIA LAB at KAIST, where I work on applications of generative models.
Use a generative prior for identity agnostic audio-driven talking-head generation with emotion manipulation while trained on a single identity dataset.
Selecting the diffusion feature and diffuse condition of stable diffusion to effectively extract sketch
Stylized and Animatable face mesh with one example.
Utilizing the generative feature to extract and edit face sketch.
Directing the user gaze to motion singularity point for VR experience.
Overlaying the difference in optical flow onto the scene for VR experience.