Image processing method, an apparatus, an electronic device, and a storage medium, with joint optimization on a depth map and a normal vector map

An electronic device, comprising:

• at least one processor;
• and
• a storage device configured to store at least one program that, when executed by the at least one processor, causes the at least one;
• input an initial depth map of a target image, a first confidence level of the initial depth map, an initial normal vector map of the target image, and a second confidence level of the initial normal vector map into an optimizer;
• perform joint optimization on a depth map and a normal vector map by the optimizer, with an objective of minimizing a difference between an optimized depth map and the depth map before being optimized and a difference between an optimized normal vector map and the normal vector map before being optimized, and an objective of minimizing an error between local planes determined from a same region in the optimized depth map and the optimized normal vector map, wherein the first confidence level and the second confidence level are weights to calculate the difference and the error;
• and
• output the optimized depth map and the optimized normal vector map by the optimizer.

A non-transitory storage medium comprising computer executable instructions that, when executed by a computer processor, causes the computer processor to:

• input an initial depth map of a target image, a first confidence level of the initial depth map, an initial normal vector map of the target image, and a second confidence level of the initial normal vector map into an optimizer;
• perform joint optimization on a depth map and a normal vector map by the optimizer, with an objective of minimizing a difference between an optimized depth map and the depth map before being optimized and a difference between an optimized normal vector map and the normal vector map before being optimized, and an objective of minimizing an error between local planes determined from a same region in the optimized depth map and the optimized normal vector map, wherein the first confidence level and the second confidence level are weights to calculate the difference and the error;
• and
• output the optimized depth map and the optimized normal vector map by the optimizer.