Large Scale 3D Morphable Models. J Booth, A Roussos, A Ponniah, D Dunaway, S Zafeiriou.
Imperial College London and Great Ormond Street build LSFM (2017), the largest 3D morphable model, with 3dMD’s real-world 12,000-scan dataset.
SMPL: A Skinned Multi-Person Linear Model. M Loper, N Mahmood, J Romero, G Pons-Moll, MJ Black.
MPI-IS trains SMPL (2015) and its DMPL extension, the field’s most widely used body model, with 3dMD’s real-world pose and motion data.
Dyna: A Model of Dynamic Human Shape in Motion. G Pons-Moll, J Romero, N Mahmood, MJ Black.
MPI-IS trains Dyna (2015), a model of soft-tissue deformation, with 3dMD’s 4D real-world body data.
FAUST: Dataset and Evaluation for 3D Mesh Registration. F Bogo, J Romero, M Loper, and MJ Black
MPI-IS builds FAUST (2014), a 3D mesh registration dataset, with 3dMD’s real-world body scan data, presented at CVPR 2014.
Florence faces: A dataset supporting 2D/3D face recognition. AD Bagdanov, A Del Bimbo, I Masi.
University of Florence builds Florence Faces (2012), a 2D/3D face recognition dataset, with 3dMD’s real-world HR facial scans.
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.
Face to face – in realistic 3D. UK experts develop super-realistic animation system.
Date: March 2005. Source: Science X, phys,org. Summary: Computing experts at Cardiff University, UK, are developing a super-realistic animation system that simulates the movements of a face, based on speech. The team in the School of Computer Science has developed highly advanced software which is continually learning the facial dynamics associated with a speaker and…