US 12,340,556 B2
System and method for correspondence map determination
Jason Devitt, Redwood City, CA (US); Haoyang Wang, Redwood City, CA (US); and Konstantin Azarov, Redwood City, CA (US)
Assigned to Compound Eye, Inc., Redwood City, CA (US)
Filed by Compound Eye, Inc., Redwood City, CA (US)
Filed on Mar. 6, 2023, as Appl. No. 18/117,672.
Application 18/117,672 is a continuation of application No. 17/246,235, filed on Apr. 30, 2021, granted, now 11,651,581.
Application 17/246,235 is a continuation of application No. 17/104,898, filed on Nov. 25, 2020, granted, now 11,030,478, issued on Jun. 8, 2021.
Claims priority of provisional application 63/072,897, filed on Aug. 31, 2020.
Claims priority of provisional application 62/941,397, filed on Nov. 27, 2019.
Prior Publication US 2023/0206594 A1, Jun. 29, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/75 (2022.01); G06N 3/08 (2023.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/751 (2022.01) [G06N 3/08 (2013.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01)] 5 Claims
OG exemplary drawing
 
1. A method comprising:
determining a pixel hash for each pixel in a first image and each pixel in a second image;
determining a first correspondence map relating matching pixels in the first and second images by, for each of a set of pixels in the first image:
determining a set of correspondence vectors for the respective pixel based on correspondence vectors of neighboring pixels, wherein each correspondence vector identifies a corresponding pixel in the second image that is paired with the respective pixel; and
selecting a correspondence vector from the set of correspondence vectors based on a cost value determined between the pixel hashes of the paired pixels;
using a neural network to generate a second correspondence map with a greater number of correspondence vectors than the first correspondence map, wherein the neural network ingests the first correspondence map and at least one of the first or second image; and
determining a dense depth map based on the second correspondence map.