US 12,266,114 B2
Image processing method and apparatus, device and storage medium
Rui Zhang, Shenzhen (CN); Pei Cheng, Shenzhen (CN); Gang Yu, Shenzhen (CN); and Bin Fu, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed on Aug. 15, 2022, as Appl. No. 17/887,994.
Application 17/887,994 is a continuation of application No. PCT/CN2021/104481, filed on Jul. 5, 2021.
Claims priority of application No. 202010718692.9 (CN), filed on Jul. 23, 2020.
Prior Publication US 2022/0398742 A1, Dec. 15, 2022
Int. Cl. G06T 7/194 (2017.01); G06T 7/11 (2017.01); G06V 10/22 (2022.01); G06V 10/26 (2022.01); G06V 10/40 (2022.01); G06V 10/776 (2022.01)
CPC G06T 7/194 (2017.01) [G06T 7/11 (2017.01); G06V 10/22 (2022.01); G06V 10/267 (2022.01); G06V 10/40 (2022.01); G06V 10/776 (2022.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An image processing method, performed by at least one processor, the method comprising:
performing preliminary segmentation recognition on a raw image by using a first segmentation model to obtain a candidate foreground image region and a candidate background image region of the raw image;
recombining the candidate foreground image region, the candidate background image region, and the raw image to obtain a recombined image, pixels in the recombined image being in a one-to-one correspondence with pixels in the raw image; and
performing region segmentation recognition on the recombined image by using a second segmentation model to obtain a target foreground image region and a target background image region of the raw image,
wherein the performing region segmentation recognition on the recombined image by using a second segmentation model to obtain a target foreground image region and a target background image region of the raw image comprises:
performing region segmentation recognition on the recombined image by using the second segmentation model to obtain a region segmentation adjustment parameter of the pixel in the recombined image; and
performing adjusted segmentation on the raw image according to the region segmentation adjustment parameter and the candidate region type probability to obtain the target foreground image region and the target background image region of the raw image.