Jump to content

18113036. SELFIE PERSPECTIVE UNDISTORTION BY 3D FACE GAN INVERSION simplified abstract (Snap Inc.)

From WikiPatents

SELFIE PERSPECTIVE UNDISTORTION BY 3D FACE GAN INVERSION

Organization Name

Snap Inc.

Inventor(s)

Jian Wang of Pittsburgh PA (US)

Zhixiang Wang of New York NY (US)

Gurunandan Krishnan Gorumkonda of Kirkland WA (US)

SELFIE PERSPECTIVE UNDISTORTION BY 3D FACE GAN INVERSION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18113036 titled 'SELFIE PERSPECTIVE UNDISTORTION BY 3D FACE GAN INVERSION

Simplified Explanation:

This patent application describes a method for correcting perspective distortion in selfie images taken at a short camera-to-face distance, making them appear as if they were taken from a longer distance.

Key Features and Innovation:

  • Processing selfie images using a pre-trained 3D face GAN.
  • Inverting the 3D face GAN to improve face latent code and camera parameters.
  • Fine-tuning a 3D face GAN generator to manipulate camera parameters for a photorealistic image.
  • Correcting distortion in various facial features such as the forehead, nose, cheeks, jawline, chin, lips, eyes, eyebrows, ears, hair, and neck.

Potential Applications:

This technology can be used in photography apps, social media platforms, and beauty enhancement tools.

Problems Solved:

The technology addresses the issue of perspective distortion in selfie images taken at a short camera-to-face distance.

Benefits:

The benefits include improved image quality, enhanced facial features, and a more natural-looking selfie.

Commercial Applications:

Potential commercial applications include selfie editing apps, virtual makeup tools, and online profile picture enhancers.

Questions about Perspective Distortion Correction: 1. How does the method described in the patent application improve the quality of selfie images? 2. What are the potential commercial uses of this technology in the beauty and photography industries?

Frequently Updated Research:

There may be ongoing research in the field of image processing and facial recognition technology that could further enhance the capabilities of this perspective distortion correction method.


Original Abstract Submitted

A method of correcting perspective distortion of a selfie image captured with a short camera-to-face distance by processing the selfie image and generating an undistorted selfie image appearing to be taken with a longer camera-to-face distance. A pre-trained 3D face GAN processes the selfie image, inverts the 3D face GAN to obtain improved face latent code and camera parameters, fine tunes a 3D face GAN generator, and manipulates camera parameters to render a photorealistic face selfie image. The processed selfie image has less distortion in the forehead, nose, cheek bones, jaw line, chin, lips, eyes, eyebrows, ears, hair, and neck of the face.

(Ad) Transform your business with AI in minutes, not months

Custom AI strategy tailored to your specific industry needs
Step-by-step implementation with measurable ROI
5-minute setup that requires zero technical skills
Get your AI playbook

Trusted by 1,000+ companies worldwide

Cookies help us deliver our services. By using our services, you agree to our use of cookies.