De-identification Ltd.

Naama Antebi

Eliran Kuta

Sella Blondheim

Gil Perry

Or Gorodissky

Yoav HaCohen

Amitay Nachmani

Matan Ben-Yosef

To consistently anonymize video, an identity-preserving encoder may be trained with a decoder to preserve identity information unique to an individual in an encoded space. The identity-preserving encoder may encode source video images of a source identity to generate identity-preserving encoded data representing the source identity. A de-identification engine may generate de-identifying encoded data representing a different target identity. A transformation may be generated based on a difference between the identity-preserving and de-identifying encoded data, representing swapping the source identity with the target identity. The identity may be consistently swapped from the source to target in the encoded space by applying the same transformation to the identity-preserving encoded data for the source images. The swapped identity encoded data may be decoded to generate consistently anonymized output images representing the non-identity information of the source images with the target identity, for all the output video images.

Facial anonymization with consistent facial attribute preservation in video

Growing community of inventors

Tel Aviv, Israel

Naama Antebi