3-dimensional digital garment creation from planar garment photographs

Abstract

Techniques for generating and presenting a three-dimensional garment model are presented herein. A communication interface can be configured to receive images, where all visible parts of the garment may be captured by the received images. A garment creation module can be configured to generate partial shapes of the garment based on the received images. Additionally, the garment creation module can determine a type of garment by comparing the generated partial shapes to a database of reference garment shapes. Furthermore, the garment creation module can generate a three-dimensional garment model by joining the partial shapes based on the determined type of garment, and can tessellate the generated three-dimensional garment model. A user interface can be configured to present the tessellated three-dimensional garment model on a three-dimensional body model.

What is claimed is: 
     
         1 . A system comprising:
 one or more processors;   a communication interface configured to:
 receive a first image depicting a first view of a garment; and 
 receive a second image depicting a second view of the garment; 
   a garment creation module that configures at least one processor among the one or more processors to:
 generate a first partial shape of the garment based on the received first image; 
 generate a second partial shape of the garment of the garment based on the received second image; 
 determine a type of garment by comparing the generated first and second partial shapes to a database of reference garment shapes; 
 generate a three-dimensional garment model by joining the first partial shape and the second partial shape based on the determined type of garment, the generated three-dimensional garment model including a first group of vertices; and 
 tessellate the generated three-dimensional garment model by adding a second group of vertices to the generated three-dimensional garment model; and 
   a user interface configured to present the tessellated three-dimensional garment model on a three-dimensional body model, the tessellated three-dimensional garment model being presented based on a simulated force.   
     
     
         2 . The system of  claim 1 , wherein the garment creation module configures the one or more processors to tessellate the generated three-dimensional garment model by tessellating the generated three-dimensional garment model into triangles, wherein vertices in the triangles correspond to points that are interior to the generated three-dimensional garment model. 
     
     
         3 . The system of  claim 2 , wherein overlaps and gaps do not exist between the triangles of the tessellated three-dimensional garment model. 
     
     
         4 . The system of  claim 2 , wherein a triangle among the triangles of the tessellated three-dimensional garment model has a minimum angle, and wherein the garment creation module further configures the one or more processors to tessellate the generated three-dimensional garment model by maximizing the minimum angle of the triangle. 
     
     
         5 . The system of  claim 1 , wherein the garment creation module configures the one or more processors to apply a texture map to the tessellated three-dimensional garment model by assigning a color to a vertex in the second group of vertices based the received first image. 
     
     
         6 . The system of  claim 1 , wherein the garment creation module configures the one or more processors to determine actual dimensions of the garment using a reference object placed near the garment in the first image. 
     
     
         7 . The system of  claim 1 , wherein the simulated force includes at least one of a gravitational force, a frictional force, or aerodynamic drag. 
     
     
         8 . The system of claim wherein the user interface is configured to present the tessellated three-dimensional garment model on the three-dimensional body model based on a material property of the garment, wherein the material property includes at least one of sheerness, linear stiffness, or bending stiffness. 
     
     
         9 . The system of  claim 1 , wherein the garment creation module configures the one or more processors to generate the first partial shape of the garment by:
 calculating a difference in color between a pixel and its adjacent pixels within the first image; and   determining that the pixel is on a first edge of the first partial shape of the garment based on the difference transgressing a predetermined threshold value.   
     
     
         10 . The system of  claim 9 , wherein the garment creation module configures the one or more processors to join the first and second partial shapes by aligning the first edge of the first partial shape with a second edge of the second partial shape. 
     
     
         11 . The system of  claim 9 , wherein the garment creation module configures the one or more processors to smooth the first edge of the first partial shape into a smoothed curve by removing artifacts in the first image, wherein the artifacts is due to a lighting effect in the first image and an image compression of the first image. 
     
     
         12 . The system of  claim 1 , wherein the garment creation module configures the one or more processors to generate a first flat-panel as the first partial shape and a second flat-panel as the second partial shape. 
     
     
         13 . The system of  claim 12 , wherein the garment creation module configures the one or more processors to generate the three-dimensional garment model by joining at least a portion of the first flat-panel with at least a portion of the second flat-panel. 
     
     
         14 . The system of  claim 1 , wherein all visible parts of the garment are captured in the received first image and received second image. 
     
     
         15 . The system of  claim 1 , wherein the communication interface is further configured to receive a third image depicting a third view of a garment, wherein all visible parts of the garment is captured by the received first image, received second image and received third image. 
     
     
         16 . The system of  claim 1 , wherein the garment creation module configures the one or more processors to generate different sized garment models by distorting the three-dimensional garment model. 
     
     
         17 . A method comprising:
 receiving a first image depicting a first view of a garment;   receiving a second image depicting a second view of the garment;   generating a first partial shape of the garment based on the received first image;   generating a second partial shape of the garment of the garment based on the received second image;   determining, by one or more processors, a type of garment by comparing the generated first and second partial shapes to a database of reference garment shapes;   generating a three-dimensional garment model by joining the first partial shape and the second partial shape based on the determined type of garment, the generated three-dimensional garment model including a first group of vertices;   tessellating the generated three-dimensional garment model by adding a second group of vertices to the generated three-dimensional garment model; and   presenting the tessellated three-dimensional garment model on a three-dimensional body model, the tessellated three-dimensional garment model being presented based on a simulated force.   
     
     
         18 . The method of  claim 17 , further comprising:
 applying a texture map to the tessellated three-dimensional garment model by assigning a color to a vertex in the second group of vertices based on the received first image.   
     
     
         19 . The method of  claim 17 , wherein the presenting the tessellated three-dimensional garment model on the three-dimensional body model is further based on calculations using a material property of the garment, wherein the material property includes at least one of sheerness, linear stiffness, or bending stiffness. 
     
     
         20 . A non-transitory machine-readable storage comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
 receiving a first image depicting a first view of a garment;   receiving a second image depicting a second view of the garment;   generating a first partial shape of the garment based on the received first image;   generating a second partial shape of the garment of the garment based on the received second image;   determining a type of garment by comparing the generated first and second partial shapes to a database of reference garment shapes;   generating a three-dimensional garment model by joining the first partial shape and the second partial shape based on the determined type of garment, the generated three-dimensional garment model including a first group of vertices;   tessellating the generated three-dimensional garment model by adding a second group of vertices to the generated three-dimensional garment model; and   presenting the tessellated three-dimensional garment model on a three-dimensional body model, the tessellated three-dimensional garment model being presented based on a simulated force.