18816630. REALISTIC NEURAL NETWORK BASED IMAGE STYLE TRANSFER (Snap Inc.)

REALISTIC NEURAL NETWORK BASED IMAGE STYLE TRANSFER

Organization Name

Snap Inc.

Inventor(s)

Jaewook Chung of Mountain View CA (US)

Christopher Yale Crutchfield of San Diego CA (US)

Emre Yamangil of San Francisco CA (US)

REALISTIC NEURAL NETWORK BASED IMAGE STYLE TRANSFER

This abstract first appeared for US patent application 18816630 titled 'REALISTIC NEURAL NETWORK BASED IMAGE STYLE TRANSFER

Original Abstract Submitted

A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.