Shape refinement of three-dimensional (3d) mesh reconstructed from images

A method, comprising:

• acquiring a set of images of an object;
• estimating a first three-dimensional (3D) mesh of a head portion of the object, based on the acquired set of images;
• executing a first set of operations on the estimated first 3D mesh to generate a second 3D mesh, wherein the executed first set of operations comprises one or more of:
• a removal of one or more regions which are unneeded for head-shape estimation, and
• a removal of one or more mesh artifacts associated with a 3D shape or a topology of the first 3D mesh;
• processing a 3D template mesh to determine a set of filling patches corresponding to a set of holes in the generated second 3D mesh;
• and
• executing, based on the generated second 3D mesh and the determined set of filling patches, a hole filling operation to generate a final 3D mesh.

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

• acquiring a set of images of an object;
• estimating a first three-dimensional (3D) mesh of a head portion of the object, based on the acquired set of images;
• executing a first set of operations on the estimated first 3D mesh to generate a second 3D mesh, wherein the executed first set of operations comprises one or more of:
• a removal of one or more regions which are unneeded for head-shape estimation, and
• a removal of one or more mesh artifacts associated with a 3D shape or a topology of the first 3D mesh;
• processing a 3D template mesh to determine a set of filling patches corresponding to a set of holes in the generated second 3D mesh;
• and
• executing, based on the generated second 3D mesh and the determined set of filling patches, a hole filling operation to generate a final 3D mesh.