Systems and methods for 2-D to 3-D image conversion using mask to model, or model to mask, conversion
View Patent ↗The present invention is directed to systems and methods for controlling 2-D to 3-D image conversion. In one embodiment, a mask is generated from an object model of the image. The mask is then used to from a 2-D mesh which is then converted to a 3-D volume mesh. The 3-D volume mesh is then used to produce 3-D image conversion.
1. A method of creating a 3-D image, said method comprising:
obtaining, from a processor-based system, object models of each said 3-D image to be created;
generating a mask from each said obtained model;
forming, from said generated mask, a 2-D mesh, in part, by using one or more grid elements, wherein said 2-D mesh comprises a number of triangles contributed by each of said one or more grid elements, and the number of triangles is based on a classification of said one or more grid elements; and
rendering a 3-D image from an assembled set of 2-D meshes.
2. The method of claim 1 wherein said mask is generated using polycurve techniques.
3. The method of claim 1 wherein said generating a mask comprises:
rendering a point cloud according to a camera model;
obtaining a boolean image from said point cloud;
identifying a sequence of boundary points in said point cloud;
obtaining a polycurve from said sequence of boundary points; and
refining said polycurve.
4. The method of claim 1 wherein said rendering a 3-D image comprises:
converting each said 2-D mesh into a 3-D planar mesh.
5. The method of claim 4 wherein said converting comprises reverse projection.
6. The method of claim 4 further comprising:
forming a 3-D mesh from said 3-D planar mesh.
7. The method of claim 6 wherein said 2-D mesh is constructed using vertices and wherein said forming a 3-D mesh comprises:
lofting by replicating surface vertices of said 2-D mesh.
8. A method of obtaining a mask for an object for creating a 3-D image, comprising:
rendering, on a processor-based system, a point cloud according to a camera model;
obtaining a boolean image from said point cloud;
identifying a sequence of boundary points in said point cloud;
obtaining said polycurve from said sequence of boundary points;
refining said polycurve to form said mask;
forming, from said mask, a 2-D mesh, in part, by using one or more grid elements,
wherein said 2-D mesh comprises a number of triangles contributed by each of said one or more grid elements, and the number of triangles is based on a classification of said one or more grid elements.
9. The method of claim 8 further comprising:
rendering said 3-D image from an assembled set of 2-D meshes.
10. The method of claim 9 wherein said rendering comprises:
converting said 2-D mesh into a 3-D volume mesh.
11. The method of claim 10 wherein said 2-D mesh is constructed using vertices and wherein said converting said 2-D mesh into a 3-D volume mesh comprises:
forming a planar 3-D mesh from said 2-D mesh; and
lofting by replicating said surface vertices of said 2-D mesh.
12. A non-transitory, machine-readable storage medium comprising instructions stored therein, the instructions executable by one or more processors to facilitate performing a method of creating a 3-D image, said method comprising:
obtaining object models of each said image to be created;
generating a mask from each said obtained model;
forming, from said generated mask, a 2-D mesh, in part, by using one or more grid elements, wherein said 2-D mesh comprises a number of triangles contributed by each of said one or more grid elements, and the number of triangles is based on a classification of said one or more grid elements; and
rendering a 3-D image from an assembled set of 2-D meshes.
13. The non-transitory, machine-readable storage medium of claim 12 wherein said mask is generated using polycurve techniques.
14. The non-transitory, machine-readable storage medium of claim 12 wherein said generating a mask comprises:
rendering a point cloud according to a camera model;
obtaining a boolean image from said point cloud;
identifying a sequence of boundary points in said point cloud;
obtaining a polycurve from said sequence of boundary points; and
refining said polycurve.
15. The non-transitory, machine-readable storage medium of claim 12 wherein said rendering a 3-D image comprises:
converting said 2-D mesh into a 3-D planar mesh.
16. The non-transitory, machine-readable storage medium of claim 15 wherein said converting comprises enabling reverse projection.
17. The non-transitory, machine-readable storage medium of claim 15 further comprising:
forming a 3-D mesh from said planar mesh.
18. The non-transitory, machine-readable storage medium of claim 17 wherein said 2-D mesh is constructed using vertices and wherein said forming a 3-D mesh comprises:
lofting by replicating surface vertices of said 2-D mesh.
19. A system for creating 3 D images, said system comprising:
a memory storing executable instructions;
one or more processors operatively coupled to the memory to execute the executable instructions from the memory, the one or more processors being configured to:
execute control sequences for obtaining object models of each said image to be created;
execute control sequences for generating a mask from each said obtained model;
execute control sequences for forming, from said generated mask, a 2-D mesh, in part, by using one or more grid elements, wherein said 2-D mesh comprises a number of triangles contributed by each of said one or more grid elements, and the number of triangles is based on a classification of said one or more grid elements; and
execute control sequences for rendering a 3-D image from an assembled set of 2-D meshes.