Monocular Identity-Conditioned Facial Reflectance Reconstruction

arXiv:2404.00301v1 Announce Type: new
Abstract: Recent 3D face reconstruction methods have made remarkable advancements, yet there remain huge challenges in monocular high-quality facial reflectance reconstruction. Existing methods rely on a large amount of light-stage captured data to learn facial reflectance models. However, the lack of subject diversity poses challenges in achieving good generalization and widespread applicability. In this paper, we learn the reflectance prior in image space rather than UV space and present a framework named ID2Reflectance. Our framework can …

arxiv cs.cv identity type