Peking University

2 Posts

Different examples of FaceShifter working on peoples' portraits
Peking University

Trading Faces: FaceShifter swaps faces obscured by objects.

AI’s ability to transfer a person’s face from a source photo onto someone in a target photo doesn’t work so well when the target face is partially obscured by, say, eyeglasses, a veil, or a hand. A new technique handles such occlusions.
An illustration of filter pruning
Peking University

High Accuracy, Low Compute

As neural networks have become more accurate, they’ve also ballooned in size and computational cost. That makes many state-of-the-art models impractical to run on phones and potentially smaller, less powerful devices.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox