MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis. A Papaioannou et al.
Imperial College London captures real-world MimicMe, a 4,700-subject 4D facial expression database, with 3dMD, presented at ECCV 2022.
Graph Convolutional Network with Probabilistic Spatial Regression: Application to Craniofacial Landmark Detection from 3D Photogrammetry. C Elkhill, S LeBeau, B French, AR Porras.
This excerpt will show up on the home page Blog/News feed
3D human tongue reconstruction from single “in-the-wild” images. S Ploumpis, S Moschoglou, V Triantafyllou, S Zafeiriou.
Imperial College London and Huawei build a 3D tongue reconstruction model with 3dMD’s real-world Science Museum, London dataset.
Convolutional Mesh Autoencoders for the 3-dimensional Identification of FGFR-related Craniosynostosis. O’Sullivan, van de Lande, Papaioannou, Breakey, Jeelani, et al.
Great Ormond Street Hospital, Imperial College London, and Alder Hey use 3dMD data to train a 3D shape-based research model for analyzing craniofacial syndromes.
Khronos Group Welcomes 3dMD as Contributor Member.
The Khronos Group is creating interoperability standards for 3D, AR/VR, vision, and machine learning.
Identity-Disentangled Neural Deformation Model for Dynamic Meshes (3DH). B Xu, L Ma, Y Ye, T Schmidt, CD Twigg, S Lovegrove.
Meta Reality Labs and Imperial College London build a neural hand deformation model with 3dMD’s real-world 3DH scan data, 2021.
3D Modeling of craniofacial ontogeny and sexual dimorphism in children. OAM Smith, YSG Nashed, C Duncan, N Pears, A Profico, P O’Higgins.
Alder Hey and University of York use 3dMD’s real-world Headspace dataset to model craniofacial growth and sexual dimorphism in children, using geometric morphometrics.
Growing Old: Do Women and Men Age Differently? OAM Smith, C Duncan, N Pears, A Profico, P O’Higgins
University of York and Alder Hey use 3dMD’s real-world Headspace dataset to model craniofacial aging across adulthood, finding men and women age in distinct, non-linear patterns.
Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis. X Liu, B Li, E Bron, W Niessen, E Wolvius, G Roshchupkin.
The proposed method was evaluated on the analysis of 3D facial shape and patient characteristics (N=5011). Experiments showed that this conceptually simple method achieved state-of-the-art fair prediction performance and interpretability, showing its great potential for clinical applications.
Anthropometric accuracy of three-dimensional average faces compared to conventional facial measurements. Z Shan, R TC Hsung, C Zhang et al.
This excerpt will show up on the home page Blog/News feed