Convolutional Point-set Representation: A Convolutional Bridge Between a Densely Annotated Image and 3D Face Alignment

no code implementations • 17 Mar 2018 • Yuhang Wu, Le Anh Vu Ha, Xiang Xu, Ioannis A. Kakadiaris

The method relies on Convolutional Point-set Representation (CPR), a carefully designed matrix representation to summarize different layers of information encoded in the set of detected points in the annotated image.

3D Face Alignment Face Alignment