Method for training depth estimation model, electronic device and readable storage medium
AssigneeHon Hai Precision Industry Co., Ltd.
InventorsJUNG-HAO YANG, CHIH-TE LU, CHIN-PIN KUO
Life of this patent
Estimating the term…
Loading patent…
AssigneeHon Hai Precision Industry Co., Ltd.
InventorsJUNG-HAO YANG, CHIH-TE LU, CHIN-PIN KUO
Estimating the term…
A method for training a depth estimation model is provided. The method includes obtaining a first left image and a first right image. A disparity map is obtained by inputting the first left image into a depth estimation model. A second right image is obtained by adding the first left image to the disparity map. The first left image is converted into a third right image. A mask image is obtained by performing a binarization processing on a pixel value of each of pixel points of the third right image. Once a loss value of the depth estimation model is obtained by calculating a mean square error of pixel values of all corresponding pixel points of the first right image, the second right image, and the mask image, a depth estimation model is iteratively trained according to the loss value.
A method for training a depth estimation model applied to an electronic device, the method comprising:
An electronic device comprising:
A non-transitory storage medium having instructions stored thereon, when the instructions are executed by a processor of an electronic device, the processor is caused to perform a method for training a depth estimation model, wherein the method comprises:
Dependencies are inferred from the claim text.