3D microgeometry and reflectance modeling

A method, comprising:

• controlling a plurality of imaging devices arranged at a corresponding first plurality of locations on a three-dimensional (3D) structure, to capture a plurality of images from a corresponding plurality of viewpoints, wherein the plurality of images includes a first set of images of a face and a second set of images of the face;
• activating a set of flash units arranged at a corresponding second plurality of locations on the 3D structure, concurrently while the plurality of imaging devices captures the first set of images of the face;
• activating the set of flash units in a sequential pattern while the plurality of imaging devices captures the second set of images of the face;
• receiving, from the plurality of imaging devices, the plurality of images comprising the first set of images of the face and the second set of images of the face, wherein
• the face in the first set of images is exposed to omni-directional lighting and the face in the second set of images is exposed to directional lighting, and
• a light intensity of the directional lighting is greater than a light intensity of the omni-directional lighting;
• generating a 3D face mesh based on the received plurality of images;
• executing, by using the generated 3D face mesh and the second set of images, a set of skin-reflectance modeling operations to estimate a set of texture maps for the face;
• and
• texturizing the generated 3D face mesh based on the estimated set of texture maps, wherein the texturization comprises an operation in which texture information, including microgeometry skin details and skin reflectance details, of the estimated set of texture maps is mapped onto the generated 3D face mesh.

A non-transitory computer-readable medium having stored thereon, computer-executable instructions that when executed by a system, causes the system to execute operations, the operations comprising:

• controlling a plurality of imaging devices arranged at a corresponding first plurality of locations on a three-dimensional (3D) structure, to capture a plurality of images from a corresponding plurality of viewpoints, wherein the plurality of images includes a first set of images of a face and a second set of images of the face;
• activating a set of flash units arranged at a corresponding second plurality of locations on the 3D structure, concurrently while the plurality of imaging devices captures the first set of images of the face;
• activating the set of flash units in a sequential pattern while the plurality of imaging devices captures the second set of images of the face;
• receiving, from the plurality of imaging devices, the plurality of images comprising the first set of images of the face and the second set of images of the face, wherein
• the face in the first set of images is exposed to omni-directional lighting and the face in the second set of images is exposed to directional lighting, and
• a light intensity of the directional lighting is greater than a light intensity of the omni-directional lighting;
• generating a 3D face mesh based on the received plurality of images;
• executing, by using the generated 3D face mesh and the second set of images, a set of skin-reflectance modeling operations to estimate a set of texture maps for the face;
• and
• texturizing the generated 3D face mesh based on the estimated set of texture maps, wherein the texturization comprises an operation in which texture information, including microgeometry skin details and skin reflectance details, of the estimated set of texture maps is mapped onto the generated 3D face mesh.