1. A computer-implemented method comprising:
determining, from an image of the person, points that define a boundary around the person’s face;
selecting two or more different points that define the boundary of the cheeks on one side of the face, and two or more different points that define the boundary of the chin on one side of the face;
determining a single deformation factor (wi\u2014cheek) for all the selected points that define the boundary of the cheeks on one side of the face using a first equation;
determining a single deformation factor (wi\u2014chin) for all the selected points that define the boundary of the chin on one side of the face using a second equation, where the second equation is different from the first equation;
determining, for each of the selected points, a respective non-zero deformation vector) ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) based at least on a weight value factor (A) that specifies the extent to which the face is to be thinned or fattened, on the respective deformation factor (wi\u2014cheek, wi\u2014chin) for the selected point, and on a scale factor (s) that influences the respective deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) based on a size of the person’s head and that is calculated by dividing a width of the face by an adjustable parameter (B);
applying the respective deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) to each selected point to generate a face mesh of relocated points; and
generating a reshaped image of the person’s face using the face mesh.
2. The method of claim 1, wherein determining the respective non-zero deformation vector comprises determining the respective non-zero deformation vector based on a direction vector.
3. The method of claim 1, wherein applying the respective deformation vector to each selected point involves adding the respective deformation vector to each selected point.
4. The method of claim 1, comprising:
selecting two or more different points that define the boundary of the cheeks on another side of the face, and two or more different points that define the boundary of the chin on another side of the face;
determining a single deformation factor for all the selected points that define the boundary of the cheeks on the other side of the face using a third equation; and
determining a single deformation factor for all the selected points that define the boundary of the chin on the other side of the face using a fourth equation, where the third equation is different from the fourth equation.
5. The method of claim 4, comprising:
generating, using the selected points that define the boundary of the chin on one side of the face and the selected points that define the boundary of the chin on the other side of the face, two or more points that define a neck, wherein a neck height is used to generate each point that defines the neck;
determining, for each of the neck points, a non-zero neck deformation vector;
applying the respective neck deformation vector to each neck point to generate a neck mesh of relocated points; and
generating a reshaped image of the person’s neck using the neck mesh.
6. The method of claim 5, comprising merging the face mesh and the neck mesh.
7. The method of claim 5, wherein generating the points that define a neck is performed prior to applying the respective deformation vector to each selected point that defines the boundary of the cheeks of the face and that defines the boundary of the chin of the face.
8. A system comprising:
one or more computers; and
a computer-readable medium coupled to the one or more computers having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
determining, from an image of the person, points that define a boundary around the person’s face;
selecting two or more different points that define the boundary of the cheeks on one side of the face, and two or more different points that define the boundary of the chin on one side of the face;
determining a single deformation factor (wi\u2014cheek) for all the selected points that define the boundary of the cheeks on one side of the face using a first equation;
determining a single deformation factor (wi\u2014chin) for all the selected points that define the boundary of the chin on one side of the face using a second equation, where the second equation is different from the first equation;
determining, for each of the selected points, a respective non-zero deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) based at least on a weight value factor (A) that specifies the extent to which the face is to be thinned or fattened, on the respective deformation factor (wi\u2014cheek, wi\u2014chin) for the selected point, and on a scale factor (s) that influences the respective deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) based on a size of the person’s head and that is calculated by dividing a width of the face by an adjustable parameter (B);
applying the respective deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) to each selected point to generate a face mesh of relocated points; and
generating a reshaped image of the person’s face using the face mesh.
9. The system of claim 8, wherein determining the non-zero deformation vector comprises determining the non-zero deformation vector based on a direction vector.
10. The system of claim 8, wherein applying the respective deformation vector to each selected point involves adding the respective deformation vector to each selected point.
11. The system of claim 8, wherein the operations comprise:
selecting two or more different points that define the boundary of the cheeks on another side of the face, and two or more different points that define the boundary of the chin on another side of the face;
determining a single deformation factor for all the selected points that define the boundary of the cheeks on the other side of the face using a third equation; and
determining a single deformation factor for all the selected points that define the boundary of the chin on the other side of the face using a fourth equation, where the third equation is different from the fourth equation.
12. The system of claim 11, wherein the operations comprise:
generating, using the selected points that define the boundary of the chin on one side of the face and the selected points that define the boundary of the chin on the other side of the face, two or more points that define a neck, wherein a neck height is used to generate each point that defines the neck;
determining, for each of the neck points, a non-zero neck deformation vector;
applying the respective neck deformation vector to each neck point to generate a neck mesh of relocated points; and
generating a reshaped image of the person’s neck using the neck mesh.
13. The system of claim 12, wherein the operations comprise merging the face mesh and the neck mesh.
14. The system of claim 12, wherein generating the points that define a neck is performed prior to applying the respective deformation vector to each selected point that defines the boundary of the cheeks of the face and that defines the boundary of the chin of the face.
15. A computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
determining, from an image of the person, points that define a boundary around the person’s face;
selecting two or more different points that define the boundary of the cheeks on one side of the face, and two or more different points that define the boundary of the chin on one side of the face;
determining a single deformation factor (wi\u2014cheek) for all the selected points that define the boundary of the cheeks on one side of the face using a first equation;
determining a single deformation factor (wi\u2014chin) for all the selected points that define the boundary of the chin on one side of the face using a second equation, where the second equation is different from the first equation;
determining, for each of the selected points, a respective non-zero deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) based at least on a weight value factor (A) that specifies the extent to which the face is to be thinned or fattened, on the respective deformation factor (wi\u2014cheek, wi\u2014chin) for the selected point, and on a scale factor (s) that influences the respective deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) based on a size of the person’s head and that is calculated by dividing a width of the face by an adjustable parameter (B);
applying the respective deformation vector ({right arrow over (v)}d\u2014cheek, {right arrow over (v)}d\u2014chin) to each selected point to generate a face mesh of relocated points; and
generating a reshaped image of the person’s face using the face mesh.
16. The computer storage medium of claim 15, wherein the operations for determining the non-zero deformation vector comprise determining the non-zero deformation vector based on a direction vector.
17. The computer storage medium of claim 15, wherein the operations for applying the respective deformation vector to each selected point involve adding the respective deformation vector to each selected point.
18. The computer storage medium of claim 15, wherein the operations comprise:
selecting two or more different points that define the boundary of the cheeks on another side of the face, and two or more different points that define the boundary of the chin on another side of the face;
determining a single deformation factor for all the selected points that define the boundary of the cheeks on the other side of the face using a third equation; and
determining a single deformation factor for all the selected points that define the boundary of the chin on the other side of the face using a fourth equation, where the third equation is different from the fourth equation.
19. The computer storage medium of claim 18, wherein the operations comprise:
generating, using the selected points that define the boundary of the chin on one side of the face and the selected points that define the boundary of the chin on the other side of the face, two or more points that define a neck, wherein a neck height is used to generate each point that defines the neck;
determining, for each of the neck points, a non-zero neck deformation vector;
applying the respective neck deformation vector to each neck point to generate a neck mesh of relocated points; and
generating a reshaped image of the person’s neck using the neck mesh.
20. The computer storage medium of claim 18, wherein the operations comprise merging the face mesh and the neck mesh.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
That which is claimed:
1. A reversible composite fabric for use in the manufacture of military rainflies comprising:
a textile substrate having a basis weight of less than about 2 ozsq. yard, a first visual color, and first and second faces;
a base coat secured to the first face of said textile substrate and comprising a polyurethane and at least about 8% pigment when in a 40% solvent solution;
a mid-coat secured to said base coat, said mid-coat comprising a polyurethane and at least about 5% pigment when in a 40% solvent solution; and
a top coat secured to said mid-coat and comprising a polyurethane and at least about 6% pigment when in a 45% solvent solution, wherein the visual color of said top coat is visually distinct from that of said textile substrate such that opposing faces of the rainfly have different visual color appearances, and wherein each face of the fabric provides visual opacity of at least about 0.030 ft. lamberts when tested according to FED STD 191 Method 5781.
2. A reversible rainfly particularly for use in military environments comprising:
a piece of fabric at least about four feet square in size, said piece of fabric having a front fabric face and a rear fabric face, said front fabric face having a different visual color from said rear fabric face, wherein each of said fabric faces provides visual opacity and infra-red reflectance within wavelengths of at least about 600-860.
3. A process for making a composite reversible fabric having distinctly-colored first and second faces comprising the steps of:
providing a textile substrate having a basis weight of less than about 2 ounces per square yard;
dyeing said textile substrate to a first color and to provide it with a predetermined infra-red reflectance;
applying to said textile substrate a base coat comprising a polyurethane and at least about 8% solvent when in a 40% solvent solution;
applying to said base coat a mid-coat comprising a polyurethane and at least about 5% pigment when in a 40% solvent solution;
applying to said mid-coat a top coat comprising a polyurethane and at least about 6% pigment when in a 40% solvent solution, said coating having a visually distinct color from said first color of said textile substrate; and
drying the coats, to form a composite fabric having a visually distinct color on each of its faces.