US 12,602,875 B2 · Technique for three dimensional (3D) human model parsing

Abstract

Techniques and systems are provided for three-dimensional model segmentation. For instances, a process can include: rendering a three-dimensional (3D) model of an object based on a 3D mesh model and a texture of the object; generating a view of the 3D model based on the rendered 3D model; generating a texture space mask based on the texture of the object using a first machine learning (ML) model; generating a labeled mask based on a second ML model; assigning labels to the texture space mask based on the labeled mask to obtain a labeled texture space mask; and generating a 3D mask based on the labeled texture space mask.

Claims20

Dependent claims

An apparatus for three-dimensional model segmentation, the apparatus comprising:

at least one memory;
and
at least one processor coupled to the at least one memory, the at least one processor being configured to:
render a three-dimensional (3D) model of an object based on a 3D mesh model and a texture of the object;
generate a view of the 3D model based on the rendered 3D model;
generate a texture space mask based on the texture of the object using a first machine learning (ML) model;
generate a labeled mask based on a second ML model;
assign labels to the texture space mask based on the labeled mask to obtain a labeled texture space mask;
and
generate a 3D mask based on the labeled texture space mask.

7 more elements

A method for three-dimensional model segmentation, the method comprising:

rendering, using at least one processor, a three-dimensional (3D) model of an object based on a 3D mesh model and a texture of the object;
generating, using the at least one processor, a view of the 3D model based on the rendered 3D model;
generating, using the at least one processor, a texture space mask based on the texture of the object using a first machine learning (ML) model;
generating, using the at least one processor, a labeled mask based on a second ML model;
assigning, using the at least one processor, labels to the texture space mask based on the labeled mask to obtain a labeled texture space mask;
and
generating, using the at least one processor, a 3D mask based on the labeled texture space mask.

4 more elements

Dependencies are inferred from the claim text.

Technique for three dimensional (3D) human model parsing

Life of this patent

Technique for three dimensional (3D) human model parsing

Life of this patent

Abstract

Claims20