Three-dimensional point data based on stereo reconstruction using structured light

A method, comprising:

• receiving multiple sets of image data, each of the multiple sets corresponding to a respective portion of a surface of an object and a respective portion of a structured light pattern projected onto the surface;
• performing a structured light reconstruction of the multiple sets, wherein the structured light reconstruction comprises matching a first group of image pixels that correspond to a projected pixel of the structured light pattern in a first set of image data with a second group of image pixels that correspond to the projected pixel in a second set of image data;
• and
• performing stereo reconstruction of the multiple sets to generate three-dimensional (3D) point data of the surface of the object, wherein the stereo reconstruction comprises matching one or more features detected within the first group of image pixels with one or more features detected within the second group of image pixels, and wherein the stereo reconstruction restricts a correspondence search that is associated with the projected pixel and the correspondence search is restricted to exclude pixels in the first set of image data that are outside of the first group of image pixels and to exclude pixels in the second set of image data that are outside of the second group of image pixels.

A non-transitory, computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to initiate, perform, or control operations comprising:

• receiving multiple sets of image data, each of the multiple sets corresponding to a respective portion of a surface of an object and a respective portion of a structured light pattern projected onto the surface;
• performing a structured light reconstruction of the multiple sets, wherein the structured light reconstruction comprises matching a first group of image pixels that correspond to a projected pixel of the structured light pattern in a first set of image data with a second group of image pixels that correspond to the projected pixel in a second set of image data;
• and
• performing stereo reconstruction of the multiple sets to generate three-dimensional point data of the surface of the object, wherein the stereo reconstruction comprises matching one or more features detected within the first group of image pixels with one or more features detected within the second group of image pixels, and wherein the stereo reconstruction restricts a correspondence search that is associated with the projected pixel and the correspondence search is restricted to exclude pixels in the first set of image data that are outside of the first group of image pixels and to exclude pixels in the second set of image data that are outside of the second group of image pixels.