MeshGAN: Non-linear 3D Morphable Models of Faces. S Cheng, M Bronstein, Y Zhou, I Kotsia, M Pantic, S Zafeiriou.
Imperial College London trains MeshGAN (2019), a 3D face GAN, with 3dMD’s real-world 12,000-identity dataset.
Learning a Model of Facial Shape and Expression from 4D Scans. T Li, T Bolkart, MJ Black, H Li, J Romero.
MPI-IS trains FLAME (2017), a facial shape and expression model, with 3dMD’s real-world 4D pose and expression data.
A FACS Valid 3D Dynamic Action Unit Database with Applications to 3D Dynamic Morphable Facial Modeling. D Cosker, E Krumhuber, A Hilton
University of Bath and Surrey build D3DFACS (2011), the first dynamic 3D FACS dataset, with 3dMD’s real-world 4D facial data.