Abstract

Recently, Deep Neural Networks (DNNs) have been shown to outperform traditional methods in many disciplines such as computer vision, speech recognition and natural language processing. A prerequisite for the successful application of DNNs is the big number of data. Even though various facial datasets exist for the case of 2D images, there is a remarkable absence of datasets when we have to deal with 3D faces. The available facial datasets are limited either in terms of expressions or in the number of subjects. This lack of large datasets hinders the exploitation of the great advances that DNNs can provide. In this work, we overcome these limitations by introducing MimicMe, a novel large-scale database of dynamic high-resolution 3D faces. MimicMe contains recordings of 4,700 subjects with a great diversity on age, gender and ethnicity. The recordings are in the form of 4D videos of subjects displaying a multitude of facial behaviours, resulting to over 280,000 3D meshes in total. We have also manually annotated a big portion of these meshes with 3D facial landmarks and they have been categorized in the corresponding expressions. We have also built very powerful blendshapes for parameterising facial behaviour. MimicMe will be made publicly available and we envision that it will be extremely valuable to researchers working in many problems of face modelling and analysis, including 3D/4D face and facial expression recognition. We conduct several experiments and demonstrate the usefulness of the database for various applications.

Important Information

The official website for the database and all this work is here.

How to acquire the data

The MiMicME database can be obtained and used by researchers who wish to perform non-comercial research. The database includes the meshes of approximately 4,700 subjects performing various expressions and registered to a common template, metadata about their age, gender and ethnicity, and textures for the registered meshes.

The MiMicME has been freely available for research and education purposes. To obtain access to the dataset, you need to complete and sign the user agreement form (TBA in the official github repository that I mentioned previously). This agreement should be completed by a full-time academic staff member (not a student). The form should be signed, and emailed to Athanasios Papaioannou (apapaion@gmail.com) and Stefanos Zafeiriou (s.zafeiriou@imperial.ac.uk). We will verify your request and contact you on how to download the dataset. Note that the agreement requires that:

1. The dataset must be used for non-commercial research and education purposes only.

2. You agree not copy, sell, trade, or exploit the dataset for any commercial purposes.

3. In any published research using the models, you cite the following paper:

References:

If you use the above data or models, you must cite the following paper:
 

• A. Papaioannou et. al.: "Mimicme: A large scale diverse 4d database for facial expression analysis", ECCV, 2022

@inproceedings{papaioannou2022mimicme, title={Mimicme: A large scale diverse 4d database for facial expression analysis}, author={Papaioannou, Athanasios and Gecer, Baris and Cheng, Shiyang and Chrysos, Grigorios and Deng, Jiankang and Fotiadou, Eftychia and Kampouris, Christos and Kollias, Dimitrios and Moschoglou, Stylianos and Songsri-In, Kritaphat and others}, booktitle={European Conference on Computer Vision}, pages={467--484}, year={2022}, organization={Springer}}