US 12,260,577 B2
Method for training depth estimation model, method for estimating depth, and electronic device
Yu-Hsuan Chien, New Taipei (TW); and Chin-Pin Kuo, New Taipei (TW)
Assigned to HON HAI PRECISION INDUSTRY CO., LTD., New Taipei (TW)
Filed by HON HAI PRECISION INDUSTRY CO., LTD., New Taipei (TW)
Filed on Sep. 28, 2022, as Appl. No. 17/954,535.
Claims priority of application No. 202210570300.8 (CN), filed on May 24, 2022.
Prior Publication US 2023/0386062 A1, Nov. 30, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/593 (2017.01)
CPC G06T 7/593 (2017.01) [G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20228 (2013.01); G06T 2207/30252 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An electronic device comprising:
at least one processor; and
a storage device coupled to the at least one processor and storing instructions for execution by the at least one processor to cause the at least one processor to:
obtain a first image pair from a training data set, the first image pair comprising a first left image and a first right image;
input the first left image into a depth estimation model to be trained, and obtain a disparity map;
add the first left image and the disparity map, and obtain a second right image;
calculate a mean square error and a cosine similarity of pixel values of all corresponding pixels in the first right image and the second right image;
calculate mean values of the mean square error and the cosine similarity of the pixel values of all corresponding pixels in the first right image and the second right image, and obtain a first mean value of the mean square error and a second mean value of the cosine similarity;
add the first mean value and the second mean value, and obtain a loss value of the depth estimation model; and
iteratively train the depth estimation model according to the loss value.