Method and system for generating an image file of a 3D garment model on a 3D body model

A system for generating an image file of a high resolution 3D garment model on a 3D body model, the system comprising a camera, a mannequin and a processor, wherein the camera is configured to acquire at least three 2D images of a garment on the mannequin, wherein the at least three 2D images of the garment on the mannequin capture a 360° azimuthal angle range of view of the garment on the mannequin, including capturing a texture of the garment at high resolution, and wherein the processor is configured to:

• (i) create a smooth and simplified 3D garment model using the at least three 2D images of the garment;
• (ii) simulate the smooth and simplified 3D garment model on the 3D body model;
• (iii) after (ii), deform and render the high-resolution garment texture on the simulated smooth and simplified 3D garment model on the 3D body model, and
• (iv) generate an image file of the 3D body model, the image file including the deformed and rendered high-resolution garment texture, on the simulated smooth and simplified 3D garment model, on the 3D body model in which in (i), to create the smooth and simplified 3D garment model using the at least three 2D images of the garment, the shape-from-silhouettes (SfS) approach is used.

A computer program product for generating an image file of a high resolution 3D garment model on a 3D body model, the computer program product embodied on a non-transitory storage medium, in which at least three 2D images of a garment on a mannequin have been acquired, wherein the at least three 2D images of the garment on the mannequin capture a 360° azimuthal angle range of view of the garment on the mannequin, including capturing a texture of the garment at high resolution;

• wherein the computer program product is executable on a processor to:
• (i) create a smooth and simplified 3D garment model using the at least three 2D images of the garment;
• (ii) simulate the smooth and simplified 3D garment model on the 3D body model;
• (iii) after (ii), deform and render the high-resolution garment texture on the simulated smooth and simplified 3D garment model on the 3D body model, and
• (iv) generate an image file of the 3D body model, the image file including the deformed and rendered high-resolution garment texture, on the simulated smooth and simplified 3D garment model, on the 3D body model;
• in which in (i), to create the smooth and simplified 3D garment model using the at least three 2D images of the garment, the shape-from-silhouettes (SfS) approach is used.

A method of generating an image file of a high resolution 3D garment model on a 3D body model, the method comprising the steps of:

• (i) acquiring at least three 2D images of a garment on a mannequin, wherein the at least three 2D images of the garment on the mannequin capture a 360° azimuthal angle range of view of the garment on the mannequin, including capturing a texture of the garment at high resolution;
• (ii) creating a smooth and simplified 3D garment model using the at least three 2D images of the garment;
• (iii) simulating the smooth and simplified 3D garment model on the 3D body model;
• (iv) after step (iii), deforming and rendering the high-resolution garment texture on the simulated smooth and simplified 3D garment model on the 3D body model, and
• (v) generating an image file of the 3D body model, the image file including the deformed and rendered high-resolution garment texture, on the simulated smooth and simplified 3D garment model, on the 3D body model;
• in which 3D morphable garment templates are defined for each typical garment type, and in which each 3D morphable garment template comprises one base shape and K morph end points.

A method of generating an image file of a high resolution 3D garment model on a 3D body model, the method comprising the steps of:

• (i) acquiring at least three 2D images of a garment on a mannequin, wherein the at least three 2D images of the garment on the mannequin capture a 360° azimuthal angle range of view of the garment on the mannequin, including capturing a texture of the garment at high resolution;
• (ii) creating a smooth and simplified 3D garment model using the at least three 2D images of the garment;
• (iii) simulating the smooth and simplified 3D garment model on the 3D body model;
• (iv) after step (iii), deforming and rendering the high-resolution garment texture on the simulated smooth and simplified 3D garment model on the 3D body model, and
• (v) generating an image file of the 3D body model, the image file including the deformed and rendered high-resolution garment texture, on the simulated smooth and simplified 3D garment model, on the 3D body model;
• in which a constrained physics simulation is performed, i.e. using a low level-of-detail simulation, to smoothly deform the garment so that it addresses the change of body shape, and in which a gravity parameter is set to zero, or near to zero, in the constrained physics simulation to avoid a double-draping artifact.

A method of generating an image file of a high resolution 3D garment model on a 3D body model, the method comprising the steps of:

• (i) acquiring at least three 2D images of a garment on a mannequin, wherein the at least three 2D images of the garment on the mannequin capture a 360° azimuthal angle range of view of the garment on the mannequin, including capturing a texture of the garment at high resolution;
• (ii) creating a smooth and simplified 3D garment model using the at least three 2D images of the garment;
• (iii) simulating the smooth and simplified 3D garment model on the 3D body model;
• (iv) after step (iii), deforming and rendering the high-resolution garment texture on the simulated smooth and simplified 3D garment model on the 3D body model, and
• (v) generating an image file of the 3D body model, the image file including the deformed and rendered high-resolution garment texture, on the simulated smooth and simplified 3D garment model, on the 3D body model;
• in which the texture of the garment is automatically segmented, and in which a foreground of the texture of the garment is automatically segmented from the mannequin and a background using a graph-cut algorithm.