Reconstruction of object surfaces from a point cloud by employing regional level sets

A method for reconstruction a surface of an object, the method comprising:

• steps for generating, based on a detection of a plurality of photons, a point cloud;
• steps for generating, based on the generated point cloud, an object model;
• steps for reconstructing, based on the object model, a surface of the object;
• and
• steps for displaying a visual representation of the reconstruction of the object.

A computing system comprising:

• a processor device;
• and
• a non-transitory computer-readable storage medium, coupled with the processor device, having instructions stored thereon, which, when executed by the processor device, provide the system with one or more engines configured for reconstructing a surface of an object by performing actions comprising:
• detecting a plurality of photons that are reflected from a surface of an object, wherein the object is located within a space;
• accessing a point cloud that is based on the detected plurality of photons;
• iteratively generating, based on the point cloud, a model of the object that includes a regional level set (RLS), wherein the RLS includes a region identification (ID) and a corresponding indicator value for each of a plurality of spatial coordinates of the space;
• and
• employing the model to cause display of a visual representation of the object.