Image processing method, device and computer-readable storage medium

An electronic device, comprising:

• at least one processing circuit configured to:
• obtain a first reference image and a second reference image of a reference object, the first reference image and the second reference image being captured by a reference camera at different positions relative to the reference object;
• determine a first constraint and a second constraint based on the first reference image and the second reference image, the first constraint being related to a difference between different depth maps of the same reference images, and the second constraint being related to depth consistency of different reference images;
• train a depth estimation model at least based on the first constraint and the second constraint, to obtain the trained depth estimation model,
• obtain a first sparse depth map and a first dense depth map corresponding to the first reference image, and a second sparse depth map and a second dense depth map corresponding to the second reference image;
• determine the first constraint based on the first sparse depth map, the first dense depth map, the second sparse depth map and the second dense depth map;
• and
• determine the second constraint based on the first dense depth map and the second dense depth map.

A computer-readable storage medium having machine-executable instructions stored thereon, the machine-executable instructions, when executed by a device, causing the device to:

• obtain a first reference image and a second reference image of a reference object, the first reference image and the second reference image being captured by a reference camera at different positions relative to the reference object;
• determine a first constraint and a second constraint based on the first reference image and the second reference image, the first constraint being related to a difference between different depth maps of the same reference images, and the second constraint being related to depth consistency of different reference images;
• train a depth estimation model at least based on the first constraint and the second constraint, to obtain the trained depth estimation model;
• obtain a first sparse depth map and a first dense depth map corresponding to the first reference image, and a second sparse depth map and a second dense depth map corresponding to the second reference image;
• determine the first constraint based on the first sparse depth map, the first dense depth map, the second sparse depth map and the second dense depth map;
• and
• determine the second constraint based on the first dense depth map and the second dense depth map.