US 12,456,169 B2
Image processing method and apparatus
Feida Zhu, Beijing (CN); Ying Tai, Beijing (CN); Chengjie Wang, Beijing (CN); and Jilin Li, Beijing (CN)
Assigned to Tencent Cloud Computing (Beijing) Co., Ltd., Beijing (CN)
Filed by Tencent Cloud Computing (Beijing) Co., Ltd., Beijing (CN)
Filed on Mar. 31, 2023, as Appl. No. 18/129,213.
Application 18/129,213 is a continuation of application No. PCT/CN2021/108489, filed on Jul. 26, 2021.
Claims priority of application No. 2021106203828 (CN), filed on Jun. 3, 2021.
Prior Publication US 2023/0237630 A1, Jul. 27, 2023
Int. Cl. G06T 5/50 (2006.01); G06T 5/77 (2024.01); G06T 7/11 (2017.01); G06T 9/00 (2006.01); G06V 10/25 (2022.01); G06V 10/74 (2022.01)
CPC G06T 5/50 (2013.01) [G06T 5/77 (2024.01); G06T 7/11 (2017.01); G06T 9/00 (2013.01); G06V 10/25 (2022.01); G06V 10/761 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20221 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An image processing method, comprising:
processing, with a first generator in an image processing model, a first sample image xi in a first sample set to obtain a first predicted image x′i, the first predicted image x′i comprising a first predicted avatar, the first sample set comprising N first sample images, each of the first sample images comprising a target avatar corresponding to a same target user, N being a positive integer, i being a positive integer, and i≤N;
processing, with the first generator, a second sample image yk in a second sample set to obtain a second predicted image y′k, the second predicted image y′k comprising a second predicted avatar; the second sample set comprising M second sample images, each of the second sample images comprising a sample avatar, M being a positive integer, k being a positive integer, and k≤M; and
training the image processing model according to a difference between the target avatar in the first sample image xi and the first predicted avatar and a difference between a first type attribute of the sample avatar in the second sample image yk and a first type attribute of the second predicted avatar, the image processing model being configured to replace an avatar in an input image with the target avatar and retain the first type attribute of the avatar in the input image.