Date: November 2022.
Source: Computer Vision – ECCV 2022. Lecture Notes in Computer Science, vol 13668. Springer, Cham. https://doi.org/10.1007/978-3-031-20074-8_27.
Research Summary: MimicMe addresses the shortage of large-scale 3D/4D facial datasets needed to train Deep Neural Networks (DNNs), which have outperformed traditional methods across computer vision, speech recognition, and natural language processing but require substantial data to do so. Existing real-world 3D facial datasets are limited in either the range of expressions or the number of subjects. MimicMe introduces a large-scale database of dynamic, high-resolution, real-world 3D faces from 4,700 subjects with wide diversity in age, gender, and ethnicity, captured as a progressive 3D scan sequence totaling over 280,000 3D/4D scans. A large portion of the scans are manually annotated with 3D facial landmarks and categorized by expression, and the dataset includes blendshapes for parameterizing facial behavior.
3dMD’s Role: MimicMe’s dataset, 4,700 subjects and over 280,000 3D scans, was captured during a 2017 facial expression exhibition with Imperial College London at the Science Museum, London, on a 3dMDface.t system running at 10fps. ImHead (2025), a later Imperial College London paper, independently confirms this same system and dataset in its own methods.

Article: MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis.
Authors: Athanasios Papaioannou, Baris Gecer, Shiyang Cheng, Grigorios Chrysos, Jiankang Deng, Eftychia Fotiadou, Christos Kampouris, Dimitrios Kollias, Stylianos Moschoglou, Kritaphat Songsri-In, Stylianos Ploumpis, George Trigeorgis, Panagiotis Tzirakis, Evangelos Ververas, Yuxiang Zhou, Allan Ponniah, Anastasios Roussos, and Stefanos Zafeiriou. Imperial College London, London, UK.

Related Articles:

  1. ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling. RA Potamias, S Galanakis, J Deng, A Papaioannou, S Zafeiriou.
  2. Facial asymmetry in syndromic craniosynostosis patients undergoing midface surgery compared to a large general population. P Rostamzad, X Liu, EB Wolvius, MM Pleumeekers, G Roshchupkin, T Abdel-Alim.
  3. Using Facial Morphology Traits Related to Attention Problems in Children to Identify Prenatal Exposures History. A Shchetinina, X Liu, N Slopen, C Chambers, M Kayser, E Wolvius, G Roshchupkin, H Tiemeier.
  4. Deep learning predicted perceived age is a reliable approach for analysis of facial ageing: A proof of principle study. C Turner, LM Pardo, DA Gunn, R Zillmer, S Mekić, F Liu, MA Ikram, CCW Klaver, PH Croll, A Goedegebure, K Trajanoska, F Rivadeneira, M Kavousi, GGO Brusselle, M Kayser, T Nijsten, J Bacardit.