System and method for rendering clothing on a two-dimensional image

A computer-implemented method for rendering clothing on a two-dimensional image, comprising:

• receiving at least one depth frame of a photography subject;
• generating a virtual avatar based on the at least one depth frame, wherein the virtual avatar includes a digital three-dimensional mesh;
• receiving a digital three-dimensional model of an article of clothing;
• manipulating the digital three-dimensional model of the article of clothing to fit on the virtual avatar;
• calculating lighting data based on content included in the at least one depth frame;
• rendering the three-dimensional model of the article of clothing into a two-dimensional image based on the lighting data;
• and
• overlaying the two-dimensional image onto a two-dimensional version of the at least one depth frame;
• wherein manipulating the digital three-dimensional model of the article of clothing to fit on the virtual avatar comprises determining a smooth bijection between a three-dimensional space of the model of the article of clothing and a three-dimensional space of the virtual avatar.

A system for-rending rendering an item on a two-dimensional image, comprising:

• a processor;
• and
• a computer-readable storage medium storing executable instructions thereon, wherein in response to the processor executing the executable instructions, the processor is configured to
• receive at least one depth frame of a photography subject,
• generate a virtual avatar based on the at least one depth frame, wherein the virtual avatar includes a digital three-dimensional mesh,
• receive a digital three-dimensional model of an item,
• manipulate the digital three-dimensional model of the item to fit on the virtual avatar,
• calculate lighting data based on content included in the at least one depth frame,
• render the three-dimensional model of the item into a two-dimensional image based on the lighting data, and
• overlay the two-dimensional image onto a two-dimensional version of the at least one depth frame;
• wherein the virtual avatar comprises a plurality of frustums and a plurality of ellipsoids.