We use Deep Learning to drive industry-leading Face Analysis and Generation

Based on a proprietary new class of deep-learning neural networks optimized to exploit geometry for speed, scale and accuracy, combined with a unique large-scale high resolution 4D dataset, Facesoft’s models have been proven in international competition to be among the best in the world. They can be used for multiple applications including facial detection, recognition, generation, expression, dense 3D motion capture and more. The Facesoft team has multiple patents pending and has published over 200 papers in the field.

The world's most accurate face recognition algorithm

In international competitions, Facesoft’s face recognition algorithms have been found to be amongst the best in the world. We combine our robust embedding networks with cutting edge large-scale search algorithms to perform real-time face recognition on a million identities.

The world's most accurate face recognition algorithm

In international competitions, Facesoft’s face recognition algorithms have been found to be amongst the best in the world. We combine our robust embedding networks with cutting edge large-scale search algorithms to perform real-time face recognition on a million identities.


We are the world leaders in facial landmark localization and tracking. Dr. Zafeiriou and his team have revolutionized the field having developed the current benchmarks in the field such as 300W, 300VW and Menpo.

Industry leading face landmark localisation

Industry leading face landmark localisation

We are the world leaders in facial landmark localization and tracking. Dr. Zafeiriou and his team have revolutionized the field having developed the current benchmarks in the field such as 300W, 300VW and Menpo.


State-of-the-art statistical 3D face models

Our 2D to 3D model software was initially developed to help with the reconstruction of patients who needed facial reconstruction surgery. Its constant developments mean its areas of application have expanded to industries such as VR gaming and film, too.

State-of-the-art statistical 3D face models

Our 2D to 3D model software was initially developed to help with the reconstruction of patients who needed facial reconstruction surgery. Its constant developments mean its areas of application have expanded to industries such as VR gaming and film, too.


Facesoft’s technology has been developed by top researchers in the field, led by Dr. Zafeiriou within the iBug group. Please visit here to see the new research of the lab.

Technology from one of the world’s best research laboratories

Technology from one of the world’s best research laboratories

Facesoft’s technology has been developed by top researchers in the field, led by Dr. Zafeiriou within the iBug group. Please visit here to see the new research of the lab.