The Headspace dataset

Christian Duncan, Rachel Armstrong, Alder Hey Craniofacial Unit, Liverpool, UK

Nick Pears, Hang Dai, Will Smith, Department of Computer Science, University of York, UK

Supported by QIDIS and Google Faculty Awards

The Headspace dataset is a set of 3D images of the human head, consisting of 1519 subjects wearing tight fitting latex caps to reduce the effect of hairstyles. The dataset is free for University-based non-commercial research. It can only be requested by academics that are verifiable university employees using the same user agreement form as for the LYHM model. Students must get their academic supervisors to request the data. An email linked to a Google account must be supplied to allow the distribution via Google drive. The download file is a compressed tarball (.tar.gz), with file size 38GB. The indices of the 1212 subjects that we used for the LYHM 3D Morphable Model (3DMM) are provided with the dataset.

There are various auxiliary components of the dataset available in request, which includes:

The data collection was planned and implemented by the Alder Hey Craniofacial Unit, under the direction of Christian Duncan, lead Craniofacial clinician. The process employed 3dMD's static 3dMDhead scanning system to capture 1519 3D images of the human head (filtered to 1212 images for our global 3D Morphable Model build). The initial collection was supported by QIDIS and the work in 2017-18 was supported by Google Faculty Awards in the 'Headspace Online' project, with sponsor Forrester Cole (Google, Cambridge, MA).

Headspace data formats

The data is in OBJ format with BMP textures and is available online for download.

Directories are per subject and named with subject indices from 00001 to 01519. Within each directory are the following files, where root is 12 digit 3D image identifier.

The dataset is supplied with subject-based and capture-based metadata in the file 'subject.txt'. The subject information includes: gender, declared ethnic group, age, eye color, hair color, beard descriptor (none, low, medium, high), moustache descriptor (none, low, medium, high), and a spectacles flag. The capture information contains a quality descriptor (free text, such as `data spike right upper lip'), a hair bulge flag (hair bulge under latex cap distorting the apparent cranial shape), a cap artefact flag (cap has a ridge at its apex due to poor fitting), a cranial hole flag (a missing part in the data scan at the cranium) and an under chin hole flag (missing part under chin).

Matlab code is included for viewing the dataset, or other utilities can be used, such as MeshLab.

Data example, subject 01242 (Christian Duncan)




FLAME model registrations and parameters from the MICA project - ECCV 2022

Wojciech Zielonka, Timo Bolkart and Justus Thies have kindly provided a set of FLAME model registrations and FLAME model parameters for the Headspace dataset via the MICA project. These registrations are shown in the figure below. Please indicate if you want these FLAME registrations and parameters to be included in your dataset distribution using the download selection table on the agreement form. The same restrictions apply as for the raw data, in that these meshes are for non-commercial, University-based research use only. If they are employed in your research, then you should cite the following MICA project publication,

also citing the following Dai et al 2020 IJCV paper for primary Headspace data:




The REALY benchmark - ECCV 2022

The REALY project presents a region-aware evaluation with publicly-available code for 3D face reconstruction. It employs 100 scans from the Headspace dataset and is published at ECCV 2022.

Please indicate if you want to use the REALY benchmark for evaluation on the user agreement form. The same restrictions apply as for the raw data, in that these meshes are for non-commercial, University-based research use only. If they are employed in your research, then you should cite the following REALY project publication:

also citing the following Dai et al 2020 IJCV paper for primary Headspace data:

After unzipping the REALY download file, you will find three folders, as follows:

  1. REALY_scan_region/
    • This folder contains facial regions (i.e., nose, mouth, forehead, cheek) of 100 scans from the Headspace dataset.
  2. REALY_HIFI3D_keypoints/
    • This folder contains 85 keypoints of 100 scans from the registered HIFI3D mesh.
  3. REALY_image/
    • This folder contains images rendered from 100 textured scans. "image_depth_*" contains the rendered images and ground-truth depth in 512x512 resolution. "crop_image*" contains the cropped rendered images in 512x512 resolution.

Figure: Examples of the REALY benchmark: First row: globally aligned high-resolution scans with textures. Second row: retopologized meshes in HIFI3D topology with semantically consistent keypoints (red points). Third row: high quality face region masks of each scan.
Figure: The REALY benchmark uses multi-view rendered portraits images of 100 high quality scans from Headspace to evaluate 3D face reconstruction accuracy. Rows 1-4: multi-view images of each scan. Row 5: frontal images of each scan.



Pose normalised images with and without landmarks (provided by Zach Fishman)

These are useful for visual indexing of the dataset and visually checking the correctness of the meta data and automatic landmark extraction. They were kindly provided by Zach Fishman working with Prof Cari Whyne at the Orthopaedic Biomechanics Lab, Sunnybrook Research Institute and University of Toronto. If you want these images and the spreadsheet summarising the subject/image meta data, please indicate this in the download selection table on the user agreement form.




Dataset version information (subject meta data correction in version 02)

Early releases of the dataset (version 1 - pre August 2018) have 1518 subject ID directories, whilst later releases (v02) have 1519. This is because one OBJ file was put in the wrong subject ID directory on collection, and hence associated with the wrong subject meta-data (age, gender, etc). This is an 8-year old girl (meta data here), who was in the directory of a 26 year old male (meta data here). Her scan is moved from subject ID 01400 to 01519 in the v02 release, and the correct meta data of the 26 year-old male is now associated with subject 01400.

This is only important if you are using subject 1400 and the meta data. In this case you can clearly use ensure the correct meta data is being used by visual inspection.

York/Alder Hey publications using the Headspace dataset

Please cite the 2020 IJCV paper, first in the list below, if you are using our models and/or dataset.

3D morphable models

  1. Statistical Modeling of Craniofacial Shape and Texture
      H. Dai, N. E. Pears, W. Smith and C. Duncan
      International Journal of Computer Vision (2020)
      [DOI][BibTeX]

  2. Symmetric Shape Morphing for 3D Face and Head Modelling
      H. Dai, N. E. Pears, W. Smith and C. Duncan
      Proc. 2018 IEEE Int. Conf. Automatic Face and Gesture Recognition (FG 2018)

  3. A 3D Morphable Model of Craniofacial Shape and Texture Variation
      H. Dai, N. E. Pears, W. Smith and C. Duncan
      Proc. 2017 Int. Conf. Computer Vision (ICCV 2017)
      [PDF][BibTeX]

  4. Symmetry-factored Statistical Modelling of Craniofacial Shape
      H. Dai, W. Smith, N. E. Pears, and C. Duncan
      Proc. 2017 PeopleCap Workshop, Int. Conf. Computer Vision (ICCV 2017) pp. 786-794
      [PDF][BibTeX]

2D morphable models

  1. Modelling of Orthogonal Craniofacial Profiles
      H. Dai, N. E. Pears and C. Duncan
      Journal of Imaging, vol 3, number 55 (2017)
      [PDF][DOI][BibTeX]

  2. A 2D Morphable Model of Craniofacial Profile and Its Application to Craniosynostosis
      H. Dai, N. E. Pears and C. Duncan
      Proc. 2017 Conf. Medical Image Understanding and Analysis (MIUA 2017).
      Communications in Computer and Information Science, pages 731-742, vol 723. Springer, Cham
      [DOI]

Clinical abstracts

  1. A Morphable Model Of the Human Head Vaidating the Outcomes of An Age-Dependant Scaphocephaly Correction
      B. Robertson, H. Dai, N. E. Pears and C. Duncan
      Abstract in International Journal of Oral and Maxillofacial Surgery (vol 46, p68, 2017).
      [DOI]

  2. A Morphable Profile Model of the Human Head as an Outcome Tool for Craniosynostosis Surgery
      Christian Duncan, Rachel Armstrong (Alder Hey Hospital, Liverpool) and Nick E. Pears
      16th Biennial Congress of the International Society of Craniofacial Surgery (ISCFS), Tokyo Bay, Japan, September 14th - 18th, 2015.
      Poster abstract P74 (page e91) in British Journal of Oral and Maxillofacial Surgery 54 (2016).
      [DOI]

Inital arXiv publication

Our arXiv paper details our early 100-subject prototype models that were developed in 2015, and can be found here.

  1. Automatic 3D modelling of craniofacial form
      N. E. Pears and C. Duncan
      arXiv, 21st Jan 2016
      [arXiv]

Project sponsors

We thank the funding bodies that have supported this research which include

BACK to Nick Pears' Research Projects page.