Deep learning method developed for 3D reconstruction of faces

The new approach to 3D face scanning uses deep learning, auto-labeled synthetic data and unlabelled real data

The new approach to 3D face scanning uses deep learning, auto-labeled synthetic data and unlabelled real data

The domain-adaptive reconstruction method has helped researchers to overcome training limitations that existed in previous methods due to the scarcity of real depth images with accurate 3D facial labels.

Welcome to Imaging and Machine Vision Europe

Already registered? Sign in to continue reading

Not got an account? Register for free to continue reading

What to expect from this year’s Vision show

The recent Vision/VDMA round table event in Stuttgart brought together VDMA members, members of the Vision Advisory Board, alongside key association partners and members of the press for a sneak preview of what to expect at this year’s Vision event, and an update on the state of the market.

Editor's picks

What to expect from this year’s Vision show