AI RESEARCH

PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction

arXiv CS.CV

ArXi:2604.13918v1 Announce Type: new We present PartNerFace, a part-based neural radiance fields approach, for reconstructing animatable facial avatar from monocular RGB videos. Existing solutions either simply condition the implicit network with the morphable model parameters or learn an imaginary canonical radiance field, making them fail to generalize to unseen facial expressions and capture fine-scale motion details.