18353581. METHOD AND SYSTEM FOR CONVERTING SINGLE-VIEW IMAGE TO 2.5D VIEW FOR EXTENDED REALITY (XR) APPLICATIONS simplified abstract (Samsung Electronics Co., Ltd.)

METHOD AND SYSTEM FOR CONVERTING SINGLE-VIEW IMAGE TO 2.5D VIEW FOR EXTENDED REALITY (XR) APPLICATIONS

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Yingen Xiong of Mountain View CA (US)

Christopher A. Peri of Mountain View CA (US)

METHOD AND SYSTEM FOR CONVERTING SINGLE-VIEW IMAGE TO 2.5D VIEW FOR EXTENDED REALITY (XR) APPLICATIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18353581 titled 'METHOD AND SYSTEM FOR CONVERTING SINGLE-VIEW IMAGE TO 2.5D VIEW FOR EXTENDED REALITY (XR) APPLICATIONS

Simplified Explanation

The method described in the abstract involves generating a stereo image pair representing a 2.5D view of a 2D image captured by an imaging sensor, by utilizing machine learning models trained to generate texture maps and depth maps for different imaging sensor poses.

• The method involves obtaining a 2D image captured by an imaging sensor and providing this image, along with the sensor pose and additional sensor poses, to a machine learning model.
• The machine learning model is trained to generate texture maps and depth maps for each sensor pose, which are then used to create a stereo image pair representing a 2.5D view of the original 2D image.
• The stereo image pair includes a pair of images with common depths associated with pixels in each collection of pixels, providing a more immersive viewing experience on XR devices.

Potential Applications

This technology could be applied in various fields such as virtual reality, augmented reality, gaming, and 3D modeling for creating realistic and immersive visual experiences.

Problems Solved

This technology solves the problem of generating 3D representations from 2D images captured by imaging sensors, allowing for more accurate depth perception and realistic rendering in XR environments.

Benefits

The benefits of this technology include enhanced visual quality, improved depth perception, and a more immersive experience for users interacting with XR devices.

Potential Commercial Applications

Potential commercial applications of this technology include XR gaming, virtual tours, architectural visualization, and medical imaging for enhanced visualization and training purposes.

Possible Prior Art

One possible prior art for this technology could be the use of machine learning models to generate depth maps and texture maps for 3D reconstruction from 2D images in the field of computer vision.

How does this technology impact the development of XR devices in the future?

This article does not delve into the potential long-term effects of this technology on the advancement of XR devices and their applications.

What are the limitations of using machine learning models for generating texture maps and depth maps in this context?

The article does not address any potential drawbacks or limitations of utilizing machine learning models for creating texture and depth maps for 2.5D image representations.

Original Abstract Submitted

A method includes obtaining a 2D image captured using an imaging sensor. The 2D image is associated with an imaging sensor pose. The method also includes providing the 2D image, the imaging sensor pose, and one or more additional imaging sensor poses to at least one machine learning model that is trained to generate a texture map and a depth map for the imaging sensor pose and each additional imaging sensor pose. The method further includes generating a stereo image pair based on the texture maps and the depth maps. The stereo image pair represents a 2.5D view of the 2D image. The 2.5D view includes a pair of images each including multiple collections of pixels and, for each collection of pixels, a common depth associated with the pixels in the collection of pixels. In addition, the method includes initiating display of the stereo image pair on an XR device.