Abstract: Pose variant or self-occlusion is one of the open issues which severely degrades the performance of pose-invariant face recognition (PIFR). Existing solutions to PIFR either have undesirable ...

In this paper, we propose a clean yet effective framework to generate pose-controllable talking faces. We operate on non-aligned raw face images, using only a single photo as an identity reference.

Covering everything from pose reference websites and anatomy books to digital tools and mobile apps, this roundup helps artists at all levels find accurate, inspiring materials to practice from.