Method for training depth estimation model, training apparatus, and electronic device applying the method

A training apparatus configured for a depth estimation network, the training apparatus comprises a storage medium and at least one processor;

• the storage medium stores at least one command;
• the at least one commands is implemented by the at least one processor to execute functions;
• the storage medium comprising:
• an image acquiring module configured to acquire a first image and a second image of a target object, the first image and the second image being images captured at different time points;
• a depth acquiring module configured to input the first image into a depth estimation network and obtain a depth image;
• a posture acquiring module configured to input the first image and the second image into the depth estimation network and obtain a pixel posture conversion relationship between the first image and the second image, wherein the pixel posture conversion relationship comprises a position relationship between each first pixel in the first image and a corresponding second pixel in the second image;
• the first pixel and the second pixel correspond to a same part of the target object;
• a generating module configured to generate a restored image based on the depth image, the pixel posture conversion relationship, and pre-obtained camera parameters;
• a determining module configured to determine a loss of the depth estimation network based on a difference between the first image, the depth image, the restored image, and the second image;
• and
• an adjusting module configured to adjust parameters of the depth estimation network based on the loss of the depth estimation network.

An electronic device comprises:

• a storage medium;
• and
• a processor,
• wherein the storage medium stores computer programs, and
• the processor executes the computer programs to implement the following processes:
• acquiring a first image and a second image of a target object, the first image and the second image being images captured at different time points;
• inputting the first image into a depth estimation network and obtaining a depth image;
• inputting the first image and the second image into the depth estimation network, and obtaining a pixel posture conversion relationship between the first image and the second image, wherein the pixel posture conversion relationship comprises a position relationship between each first pixel in the first image and a corresponding second pixel in the second image;
• the first pixel and the second pixel correspond to a same part of the target object;
• generating a restored image based on the depth image, the pixel posture conversion relationship, and pre-obtained camera parameters;
• determining a loss of the depth estimation network based on a difference between the first image, the depth image, the restored image, and the second image;
• and
• adjusting parameters of the depth estimation network based on the loss of the depth estimation network.