Method and system for vision based 3D reconstruction and object tracking

A computer readable medium comprising computer readable code executable by one or more processors to:

• obtain a first image of an object captured by a first camera of an electronic device, the first camera facing a first direction;
• obtain a second image of the object captured by a second camera of the electronic device, the second camera facing a second direction, wherein the second camera captures the second image of the object as a reflection in a mirror;
• determine a virtual baseline distance between the first camera and the second camera based on an apparent distance of the first camera to the second camera as reflected in the mirror based on a reflected distance of at least part of the electronic device in the second image and a known spatial relationship between the first camera and the at least part of the electronic device;
• and
• generate at least a partial 3D model of the object using the first image, the second image, and the virtual baseline distance.

A system for 3D model construction, comprising:

• a first camera of an electronic device directed in a first direction;
• a second camera of the electronic device directed in a second direction;
• one or more processors;
• and
• a memory coupled to the one or more processors and comprising computer readable code executable by the one or more processors to:
• obtain a first image of an object captured by the first camera;
• obtain a second image of the object captured by the second camera as a reflection in a mirror in front of the first camera;
• determine a virtual baseline distance between the first camera and the second camera based on an apparent distance of the first camera to the second camera as reflected in the mirror based on a reflected distance of at least part of the electronic device in the second image and a known spatial relationship between the first camera and the at least part of the electronic device;
• and
• generate at least a partial 3D model of the first object using the first image, the second image, and the virtual baseline distance.