US 12,254,633 B2
Segmenting objects using scale-diverse segmentation neural networks
Scott Cohen, Sunnyvale, CA (US); Long Mai, Portland, OR (US); Jun Hao Liew, Singapore (SG); and Brian Price, San Jose, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 18, 2022, as Appl. No. 17/655,493.
Application 17/655,493 is a continuation of application No. 16/231,746, filed on Dec. 24, 2018, granted, now 11,282,208.
Prior Publication US 2022/0207745 A1, Jun. 30, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/12 (2017.01); G06T 3/4046 (2024.01); G06T 7/194 (2017.01); G06V 10/20 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01); G06V 10/24 (2022.01)
CPC G06T 7/12 (2017.01) [G06T 3/4046 (2013.01); G06T 7/194 (2017.01); G06V 10/255 (2022.01); G06V 10/454 (2022.01); G06V 10/82 (2022.01); G06T 2207/20081 (2013.01); G06V 10/248 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
segmenting one or more objects in a digital image at a first scale by utilizing a scale-diverse segmentation neural network to generate a first object segmentation output at the first scale utilizing the digital image and a first scale indicator as input;
segmenting the one or more objects in the digital image at a second scale by utilizing the scale-diverse segmentation neural network to generate a second object segmentation output at the second scale utilizing the digital image and a second scale indicator as input;
providing a set of interactive object segmentation outputs representing the first object segmentation output and the second object segmentation output of the scale-diverse segmentation neural network for display at the first scale and the second scale in a graphical user interface of a client device;
receiving, from the client device, a client device interaction selecting the first object segmentation output or the second object segmentation output of the scale-diverse segmentation neural network; and
generating, based on the client device interaction, the first object segmentation output or the second object segmentation output for display within the digital image in the graphical user interface.