US 11,734,828 B2
High quality instance segmentation
Namdar Homayounfar, Toronto (CA); Yuwen Xiong, Toronto (CA); Justin Liang, Toronto (CA); Wei-Chiu Ma, Toronto (CA); and Raquel Urtasun, Toronto (CA)
Assigned to UATC, LLC, Mountain View, CA (US)
Filed by UATC, LLC, Mountain View, CA (US)
Filed on Aug. 1, 2022, as Appl. No. 17/878,408.
Application 17/878,408 is a continuation of application No. 17/017,104, filed on Sep. 10, 2020, granted, now 11,410,315.
Claims priority of provisional application 63/024,847, filed on May 14, 2020.
Claims priority of provisional application 62/936,448, filed on Nov. 16, 2019.
Prior Publication US 2022/0383505 A1, Dec. 1, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/11 (2017.01); G06T 7/73 (2017.01); G06V 10/77 (2022.01); G06F 18/24 (2023.01); G06F 18/213 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)
CPC G06T 7/11 (2017.01) [G06F 18/213 (2023.01); G06F 18/24 (2023.01); G06T 7/73 (2017.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining an image comprising a plurality of pixels;
generating, using a first portion of a machine-learned segmentation model, an initial distance function indicative of a distance of a respective pixel, of the plurality of pixels, to a predicted nearest boundary of an object depicted in the image;
generating, using a second portion of the machine-learned segmentation model, an object feature representation that comprises a feature embedding for the image;
determining, using an energy function, a final distance function based on the initial distance function and the object feature representation,
wherein the final distance function indicates that the respective pixel is associated with a background of the image or that the respective pixel is associated with the object depicted in the image; and
determining an instance segmentation mask for the image based on the final distance function.