Generating 3D Faces using Convolutional Mesh Autoencoders. A Ranjan, T Bolkart, S Sanyal, MJ Black.

Date: September 2018. Source: 15th European Conference on Computer Vision (ECCV), Munich, Germany, (pp 704-720). Abstract: Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn a latent representation of…

A scale space approach for exploring structure in spherical data. V Vuollo, L Holmström.

Date: September 2018. Source: Computational Statistics & Data Analysis, Volume 125, pp 57-69. Highlights: • A novel scale space technique for analyzing spherical data is proposed. • Distributions of normal vector directions computed from a 3dMDhead image are analyzed. • A movie is a convenient way to explore the maps included in a SphereSiZer atlas.…

An Articulating Statistical Shape Model of the Human Hand. Van Houtte J et al.

Date: July 2018. Source: International Conference on Applied Human Factors and Ergonomics (AHFE 2018). Advances in Human Factors in Simulation and Modeling. Advances in Intelligent Systems and Computing, Vol 780, pp 433-445. Springer. Abstract: This paper presents a registration framework for the construction of a statistical shape model of the human hand in a standard…

HDFD – A High Deformation Facial Dynamics Benchmark for Evaluation of Non-Rigid Surface Registration and Classification. G Andrews, S Endean, R. Dyke , Y Lai , G Ffrancon , GKL Tam.

Date: July 2018. Source: Cornell University Library – arXiv.org, Computer Science, Computer Vision. Abstract: Objects that undergo non-rigid deformation are common in the real world. A typical and challenging example is the human faces. While various techniques have been developed for deformable shape registration and classification, benchmarks with detailed labels and landmarks suitable for evaluating…

Estimating age and synthesising growth in children and adolescents using 3D facial prototypes. H Matthews, A Penington, J Clement et al.

Date: May 2018. Source: Forensic Science International, Volume 286, pp 61-69. Highlights: • Describes a framework for age estimation and growth prediction from 3D photographs. • Accuracy of both approaches is assessed. • This work can facilitate person identification and building 3D facial composites. Abstract: 3D facial images are becoming increasingly common. They provide more…

Comparison of an unsupervised machine learning algorithm and surgeon diagnosis in the clinical differentiation of metopic craniosynostosis and benign metopic ridge. MJ Cho, RR Hallac, M Effendi, JR Seaward, AA Kane.

Date: April 2018. Source: Scientific Reports, Volume 8, Article number: 6312. Abstract: Metopic suture closure can manifest as a benign metopic ridge (BMR), a variant of normal, to “true” metopic craniosynostosis (MCS), which is associated with severe trigonocephaly. Currently, there is no gold standard for how much associated orbitofrontal dysmorphology should trigger surgical intervention. In…

Genetics of the human face: Identification of large-effect single gene variants. DJM Crouch, B Winney, WP Koppen, WJ Christmas, K Hutnik, T Day, D Meena, A Boumertit, P Hysi, A Nessa, TD Spector, J Kittler, WF Bodmer.

Date: January 2018. Source: People of the British Isles, Newsletter Issue 7. Abstract: We have been studying the genetics underlying human facial features since the renewal of our PoBI grant from the Wellcome Trust in 2009. We have been doing this by going back to as many of the original volunteers as we could to…

UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition. J Deng, S Cheng, N Xue, Y Zhou, S Zafeiriou.

Date: December 2017. Source: Computing Research Repository, Cornell University – arXiv.org, Computer Vision and Pattern Recognition. Abstract: Recently proposed robust 3D face alignment methods establish either dense or sparse correspondence between a 3D face model and a 2D facial image. The use of these methods presents new challenges as well as opportunities for facial texture…

Embodied Hands: Modeling and Capturing Hands and Bodies Together. J Romero, D Tzionas, MJ Black.

Date: November 2017. Source: ACM Transactions on Graphics (TOG) – Proceedings of ACM SIGGRAPH Asia 2017. Abstract: Humans move their hands and bodies together to communicate and solve tasks. Capturing and replicating such coordinated activity is critical for virtual characters that behave realistically. Surprisingly, most methods treat the 3D modeling and tracking of bodies and…

Annotated face model-based alignment: a robust landmark-free pose estimation approach for 3D model registration. Y Wu, SK Shah, IA Kakadiaris.

Date: November 2017. Source: Machine Vision and Applications (2017). https://doi.org/10.1007/s00138-017-0887-6. Abstract: Registering a 3D facial model onto a 2D image is important for constructing pixel-wise correspondences between different facial images. The registration is based on a 3 ×× 4 dimensional projection matrix, which is obtained from pose estimation. Conventional pose estimation approaches employ facial landmarks…