US 12,462,476 B2
Method, electronic device, and computer program product for generating three-dimensional model
Zhisong Liu, Shenzhen (CN); Zijia Wang, Weifang (CN); and Zhen Jia, Shanghai (CN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Feb. 15, 2023, as Appl. No. 18/110,165.
Claims priority of application No. 202310086910.5 (CN), filed on Jan. 19, 2023.
Prior Publication US 2024/0249469 A1, Jul. 25, 2024
Int. Cl. G06T 15/04 (2011.01); G06T 15/20 (2011.01); G06T 17/00 (2006.01); G06T 19/20 (2011.01); G06V 10/40 (2022.01); G06V 10/82 (2022.01); G06V 40/10 (2022.01)
CPC G06T 17/00 (2013.01) [G06T 15/04 (2013.01); G06T 15/20 (2013.01); G06T 15/205 (2013.01); G06T 19/20 (2013.01); G06V 10/40 (2022.01); G06V 10/82 (2022.01); G06V 40/10 (2022.01); G06T 2200/08 (2013.01); G06T 2219/20 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating a three-dimensional (3D) model, comprising:
generating, in an image encoder of a processor-based machine learning system, two-dimensional (2D) features of a 2D image on the basis of performing feature extraction on the 2D image;
generating, in the processor-based machine learning system, on the basis of the 2D features by using a symmetric conversion module of the processor-based machine learning system, 2D features subjected to symmetric conversion, wherein the symmetric conversion module is configured to generate the 2D features of an object in the 2D image in different viewing angles, the symmetric conversion module having an input coupled to an output of the image encoder; and
generating, utilizing a series arrangement of a surface decoder and a texture encoder of the processor-based machine learning system, the 3D model of the 2D image on the basis of the 2D features subjected to symmetric conversion, the surface decoder having an input coupled to an output of the symmetric conversion module, the texture encoder having an input coupled to an output of the surface decoder.