Snap Inc. (20240303843). DEPTH ESTIMATION FROM RGB IMAGES simplified abstract

From WikiPatents
Revision as of 06:59, 12 September 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

DEPTH ESTIMATION FROM RGB IMAGES

Organization Name

Snap Inc.

Inventor(s)

Riza Alp Guler of London (GB)

Dominik Kulon of London (GB)

Himmy Tam of London (GB)

Haoyang Wang of London (GB)

DEPTH ESTIMATION FROM RGB IMAGES - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240303843 titled 'DEPTH ESTIMATION FROM RGB IMAGES

    • Simplified Explanation:**

This patent application describes a system that uses image data of hands and a depth estimation model to generate extended reality effects for users during an extended reality experience.

    • Key Features and Innovation:**
  • System uses image data of hands in a real-world scene.
  • Depth estimation model trained using synthetic 2D image data with depths and segmentation masks.
  • Generates extended reality effects using image data and depth estimation model.
    • Potential Applications:**

This technology could be used in various industries such as gaming, virtual reality experiences, training simulations, and interactive learning environments.

    • Problems Solved:**

This technology addresses the need for realistic and immersive extended reality effects by utilizing hand image data and a depth estimation model.

    • Benefits:**
  • Enhances user experience during extended reality activities.
  • Provides more realistic and interactive virtual environments.
  • Improves training simulations and educational tools.
    • Commercial Applications:**

The technology could be applied in the gaming industry to create more immersive gameplay experiences, in the education sector for interactive learning tools, and in the healthcare field for training simulations.

    • Questions about Extended Reality Effects:**

1. How does the system use image data of hands to generate extended reality effects? 2. What are the potential applications of this technology beyond gaming and virtual reality experiences?


Original Abstract Submitted

a system for generating extended reality effects using image data of hands and a depth estimation model. the depth estimation model is trained using pairings of synthetic 2d image data with sets of depths and segmentation masks. an extended reality system captures image data of hands in a real-world scene and uses the image data and the depth estimation model to generate the extended reality effects. the extended reality effects are provided to a user during an extended reality experience.