Introduction
This is the website of the 3D Basel Face Model (BFM) published by the Computer Science department of the University of Basel. The Morphable Model is calculated from registered 3D scans of 100 male and 100 female faces. We distribute the BFM plus additional data for applications and experiments in academic research and education. The model and its construction are detailed in the paper "A 3D Face Model for Pose and Illumination Invariant Face Recognition".
Overview of Available Data
3D Face Scans & Renderings
- Ten registered example 3D face scans
- The scans are not included in the training set of the Morphable Model
- Renderings of the 3D face scans with systematic variations in pose and illumination
Basel Face Model
- 3D Morphable Face Model (Shape and Texture)
- Attribute vectors for gender, height, weight, and age
- Mask with four segments
- Matlab code to get started with the model
- Farkas feature point positions and vertex indices
- MPEG4-FDP feature point positions and vertex indices
- Symmetry index list
Coefficients for Face Recognition Experiments
- The 2D datasets: FERET, CMU-PIE, and BFM renderings
- The 3D UND Face Scan Database (coming soon)
Publications
A 3D Face Model for Pose and Illumination Invariant Face Recognition [PDF]
Pascal Paysan, Reinhard Knothe, Brian Amberg, Sami Romdhani, and Thomas Vetter
IN:Proceedings of the 6th IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS)
for Security, Safety and Monitoring in Smart Environments
Genova (Italy) - September 2-4, 2009
@PROCEEDINGS{bfm09,
title={A 3D Face Model for Pose and Illumination Invariant Face Recognition},
author={P. Paysan and R. Knothe and B. Amberg
and S. Romdhani and T. Vetter},
journal={Proceedings of the 6th IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS)
for Security, Safety and Monitoring in Smart Environments},
organization={IEEE},
year={2009},
address = {Genova, Italy},
}