3 papers
cs.CV2026
EGGHead: Efficient Generalizable Gaussian Heads from a Single Image
Pilseo Park, Andrew Hou, Michel Sarkis +3
Creating photorealistic human heads typically involves trade-offs between representation power, efficiency, and generalizability. Traditional mesh-based solutions relying on 3DMMs…
cs.CV2026
Learning Semantic Inpainting for Animatable Gaussian Head Avatars
Pilseo Park, Fizza Rubab, Yiying Tong
We present SInGA, a novel method for learning Semantic Inpainting for animatable Gaussian head Avatars from a single image. Existing avatar approaches often rely on multi-view obse…
cs.GR2025
Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video
Pilseo Park, Ze Zhang, Michel Sarkis +3
High-fidelity reconstruction of head avatars from monocular videos is highly desirable for virtual human applications, but it remains a challenge in the fields of computer graphics…