Snap inc. (20240378771). FAST IMAGE STYLE TRANSFERS simplified abstract

FAST IMAGE STYLE TRANSFERS

Organization Name

snap inc.

Inventor(s)

Jaewook Chung of Mountain View CA (US)

Wisam Dakka of San Francisco CA (US)

Christopher Yale Crutchfield of San Diego CA (US)

Aymeric Damien of San Francisco CA (US)

Emre Yamangil of San Francisco CA (US)

Chunhui Zhu of Burlingame CA (US)

FAST IMAGE STYLE TRANSFERS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240378771 titled 'FAST IMAGE STYLE TRANSFERS

Simplified Explanation:

This patent application describes a method for modifying an image using a convolutional neural network (CNN) based stylization process.

• The method involves capturing an image with an image sensor and saving it in the device's memory.
• A CNN-based stylization process is applied to the image in the temporary area to create a stylized version.
• The stylized image is stored as metadata to the original image.
• When instructed to display the image, both the original and stylized versions are shown.

Key Features and Innovation:

• Image modification using a CNN-based stylization process.
• Storing stylized image as metadata to the original image.
• Background process application of stylization to images.

Potential Applications:

• Photography editing applications.
• Social media platforms for enhancing images.
• Artistic image filters for mobile devices.

Problems Solved:

• Enhancing image aesthetics without manual editing.
• Streamlining the image modification process.
• Providing users with stylized image options.

Benefits:

• Automated image stylization.
• Improved visual appeal of images.
• Simplified image editing for users.

Commercial Applications:

Automated Image Stylization Process for Mobile Devices: Enhancing user experience on photography and social media apps.

Prior Art:

Prior art related to CNN-based image stylization processes in mobile devices and photography applications.

Frequently Updated Research:

Ongoing research on improving CNN-based image stylization algorithms for real-time applications.

Questions about Image Stylization:

1. How does the CNN-based stylization process differ from traditional image editing techniques? 2. What are the potential limitations of using a CNN-based stylization process for image modification?

Original Abstract Submitted

a method for modifying an image is described. the method involves capturing an image using an image sensor of a device, saving the image in a temporary area in the device's memory, then, upon storing the image in the temporary area, applying a convolutional neural network (cnn)-based stylization to the image in the temporary area as a background process of the device's processors to create a stylized image. this stylized image is then stored as metadata to the original image in the temporary area. upon receiving instructions to display the image in the temporary area on the device, the image and a thumbnail of the stylized image are displayed.