Date: October 2017
Source: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3104-3112. DOI: 10.1109/ICCV.2017.335.
Research Summary: Researchers at the University of York and Alder Hey Children’s Hospital built the Liverpool-York Head Model (LYHM), the first publicly available 3D morphable model to capture both shape and texture of the complete human head, not just the face. The team developed a fully automatic training pipeline, contributing new methods for pose normalization, dense correspondence combining both shape and texture information, and high-resolution texture mapping, generated using a pixel-embedding technique that preserves full image resolution rather than the lower-fidelity per-vertex color typically used elsewhere. Built from more than 1,200 identities in the real-world 3dMD Headspace dataset, each captured on a 3dMDhead5 System as a triangular surface of roughly 180,000 vertices, the model includes both a global head model and separate demographic sub-population models split by age and gender. Evaluation across standard shape-model metrics showed the pipeline produces state-of-the-art results.

Article: A 3D Morphable Model of Craniofacial Shape and Texture Variation.
Authors: Hang Dai, Nick Pears, William Smith, Christian Duncan. Department of Computer Science, University of York, and Alder Hey Craniofacial Unit, Liverpool.

Related Articles:

  1. The Identification of Beckwith-Wiedemann Syndrome Through Swap Disentangled Variational Autoencoder. T Rijlaarsdam, L Smith, A Rickart, S Schievano, D Dunaway, E Wolvius, L van de Lande, S Foti, J Ong.
  2. Craniofacial Symmetry Progression Following Strip Craniectomy vs. Fronto-Orbital Advancement in Unicoronal Craniosynostosis. LM Harrison, RR Hallac, AA Kane, et al.
  3. A generative model with domain adversarial training and independent conditional discriminators to predict the development of craniosynostosis. C Elkhill, IA Cruz-Guerrero, MG Linguraru, B French, AR Porras.
  4. Correction of trigonocephaly after endoscopic strip craniectomy with postoperative helmet orthosis therapy: a 3D stereophotogrammetric study. A Elawadly, L Smith, A Borghi, KI Abdelaziz, AHD Silva, DJ Dunaway, NO Jeelani, J Ong, G James.