3D system including queue management

• US 10,242,448 B2
• Filed: 10/14/2016
• Issued: 03/26/2019
• Est. Priority Date: 11/13/2015
• Status: Active Grant

• Current Assignee: VEFXi Corporation
• Original Assignee: VEFXi Corporation
• Inventors: Peterson, Craig, Lomov, Sergey, Muro, Manuel
• Primary Examiner(s): Young, Patricia I
• Application Number:
  US15/293,423
• Publication Number:
  US 20170142397A1
• Time in Patent Office: 893 Days
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: G06T 7/579 from motion
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: H04N 13/261 with monoscopic-to-stereoscopic image conversion

Abstract

A three dimensional system including queue management.

Claims

1. A method for conversion using a processor of a series of two dimensional images into a series of three dimensional images comprising:

(a) said processor receiving said series of two dimensional images having pixels where each of said series of two dimensional images are from a same viewpoint, where said series of two dimensional images do not include any images from a viewpoint other than said same viewpoint;

(b) a depth engine using said processor processing said series of two dimensional images all of which are from said same viewpoint and do not include any images from a viewpoint other than said same viewpoint to determine a respective depth map associated with each of said series of two dimensional images all of which are from said same viewpoint where said series of two dimensional images do not include any images from a viewpoint other than said same viewpoint, where said processing by said depth engine is based upon a neural network that temporally receives pixels for a selected two dimensional image and simultaneously determines said depth map for pixels of said two dimensional image that are provided to a rendering engine while still temporally receiving said pixels for said selected two dimensional image;

(c) said rendering engine using said processor processing said depth map and said pixels to render said two dimensional images all of which are from said same viewpoint and do not include any images from a viewpoint other than said same viewpoint as said series of three dimensional images where each of said series of two dimensional images are from said same viewpoint, where said series of two dimensional images do not include any images from a viewpoint other than said same viewpoint;

(d) rendering said two dimensional images all of which are from the same viewpoint and do not include any images from a viewpoint other than said same viewpoint based upon said depth map on a display.

2. The method of claim 1 wherein said processing of said depth map further including modifying said depth map that results in a different rendering than said processing of said depth map.

3. The method of claim 2 wherein said processing of said series of two dimensional images is performed in a line-by-line manner.

4. The method of claim 2 wherein said processing of said depth map is performed in a line-by-line pixel-row manner.

5. The method of claim 1 where a direct memory access table is used to write a pixel value and its associated depth to said depth map.

6. The method of claim 5 where a direct memory access is used to read said pixel value and its associated depth from said depth map.

7. The method of claim 1 where a rendering process calculates a displacement for said pixel value and its associated depth read from said depth map.

8. The method of claim 7 where said rendering engine outputs a diplacement for said pixel value and its associated depth to said output.