US 11,790,531 B2
Whole body segmentation
Gal Dudovitch, Tel Aviv (IL); Peleg Harel, Ramat Gan (IL); Chia-Hao Hsieh, Los Angeles, CA (US); Sergei Korolev, Marina del Rey, CA (US); and Ma'ayan Shuvi, Tel Aviv (IL)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Feb. 24, 2021, as Appl. No. 17/249,239.
Prior Publication US 2022/0270261 A1, Aug. 25, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/11 (2017.01); G06V 40/10 (2022.01); G06T 5/00 (2006.01); G06T 11/00 (2006.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01)
CPC G06T 7/11 (2017.01) [G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06T 5/002 (2013.01); G06T 11/00 (2013.01); G06V 40/10 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by one or more processors, a monocular image that includes a depiction of a whole body of a user;
generating, by the one or more processors, a segmentation of the whole body of the user based on the monocular image;
accessing a video feed comprising a plurality of monocular images received prior to the monocular image;
predicting, based on the plurality of monocular images received prior to the monocular image, the segmentation of the whole body of the user that is generated based on the monocular image;
smoothing the segmentation of the whole body generated based on the monocular image based on predicting the segmentation to provide a smoothed segmentation, the smoothing comprising comparing predicted one or more segmentations of whole bodies provided by a second deep neural network with the segmentation of the whole body, in the received monocular image, generated by a first deep neural network; and
applying one or more visual effects to the monocular image based on the smoothed segmentation.