US 12,347,177 B2
Method and device for 3D object detection
Yazhao Li, Tianjin (CN); and Dayu Jia, Tianjin (CN)
Assigned to Nokia Technologies Oy, Espoo (FI)
Appl. No. 17/995,932
Filed by Nokia Technologies Oy, Espoo (FI)
PCT Filed Apr. 23, 2020, PCT No. PCT/CN2020/086439
§ 371(c)(1), (2) Date Oct. 11, 2022,
PCT Pub. No. WO2021/212420, PCT Pub. Date Oct. 28, 2021.
Prior Publication US 2023/0196801 A1, Jun. 22, 2023
Int. Cl. G06V 10/82 (2022.01); G06T 7/593 (2017.01); G06T 7/73 (2017.01); G06V 10/42 (2022.01); G06V 10/77 (2022.01); G06V 10/80 (2022.01); G06V 20/64 (2022.01)
CPC G06V 10/82 (2022.01) [G06T 7/593 (2017.01); G06T 7/73 (2017.01); G06V 10/42 (2022.01); G06V 10/7715 (2022.01); G06V 10/806 (2022.01); G06V 20/64 (2022.01); G06T 2207/10012 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30252 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A method, comprising:
generating one or more fused images based on a pair of images, the pair of images including a left view image and a right view image;
extracting one or more fused features from the fused images by a single backbone network;
unmixing the fused features to a left view-aware feature and a right view-aware feature;
predicting a 3D object based on the left view-aware feature and the right view-aware feature; and
determining one or more spatial features of the predicted 3D object.