Resolution independent 3-D vectorization for graphic designs

Patent metadata

Field	Value
Publication number	US-12148089-B2
Application number	US-202217889168-A
Country	US
Kind code	B2
Filing date	Aug 16, 2022
Priority date	Aug 16, 2022
Publication date	Nov 19, 2024
Grant date	Nov 19, 2024

Abstract

Embodiments are disclosed for performing 3-D vectorization. The method includes obtaining a three-dimensional rendered image and a camera position. The method further includes obtaining a triangle mesh representing the three-dimensional rendered image. The method further involves creating a reduced triangle mesh by removing one or more triangles from the triangle mesh. The method further involves subdividing each triangle of the reduced triangle mesh into one or more subdivided triangles. The method further involves performing a mapping of each pixel of the three-dimensional rendered image to the reduced triangle mesh. The method further involves assigning a color value to each vertex of the reduced triangle mesh. The method further involves sorting each triangle of the reduced triangle mesh using a depth value of each triangle. The method further involves generating a two-dimensional triangle mesh using the sorted triangles of the reduced triangle mesh.

First claim

We claim:

1. A method comprising:
obtaining a three-dimensional rendered image and a camera position;
generating a polygonal mesh representing the three-dimensional rendered image;
creating a reduced polygonal mesh by removing one or more polygons from the polygonal mesh, wherein the one or more polygons are removed based on the camera position;
subdividing each polygon of the reduced polygonal mesh into one or more subdivided polygons wherein the one or more subdivided polygons include a number of smaller polygons formed by a number of sub-edges and connecting edges divided from each polygon of the reduced polygonal mesh, wherein the number of sub-edges divided from an edge of a polygon is defined by a proportion to a length of the edge;
performing a mapping of each pixel of the three-dimensional rendered image to the reduced polygonal mesh; and
generating a two-dimensional polygonal mesh.

2. The method of claim 1 , wherein creating a reduced polygonal mesh by removing one or more polygons from the polygonal mesh, wherein the one or more polygons are removed based on the camera position comprises:
determining that the one or more polygons are not visible to the camera using the camera position and a visible frame of the three-dimensional rendered image; and
removing the one or more polygons from the polygonal mesh.

3. The method of claim 1 , wherein the connecting edge is a second sub-edge of an adjacent smaller polygon.

4. The method of claim 1 , wherein obtaining a three-dimensional rendered image comprises performing a three-dimensional rendering on a two-dimensional vector graphic.

5. The method of claim 1 further comprising flattening the two-dimensional polygonal mesh by removing a depth value from the two-dimensional polygonal mesh, wherein the flattening is performed in a primitive space.

6. The method of claim 1 , wherein generating a two-dimensional polygonal mesh comprises:
assigning a color value to each vertex of the reduced polygonal mesh; and
sorting each polygon of the reduced polygonal mesh using a depth value of each polygon.

7. The method of claim 6 wherein assigning a color value to each vertex of the polygonal mesh comprises:
performing an inverse projection of the color value of a pixel of the three-dimensional rendered image to each vertex of the reduced polygonal mesh;
detecting a polygon of the reduced polygonal mesh that does not have an assigned color value;
identifying a nearest neighbor polygon to the polygon; and
assigning the color value of the nearest neighbor polygon to the polygon.

8. The method of claim 7 , wherein performing an inverse projection of the color value of a pixel of the three-dimensional rendered image to each vertex of the reduced polygonal mesh comprises computing a barycentric weight of each pixel for each vertex of the reduced polygonal mesh.

9. A non-transitory computer-readable storage medium including instructions stored thereon which, when executed by at least one processor, cause the at least one processor to:
obtain a three-dimensional rendered image and a camera position;
obtain a triangle mesh representing the three-dimensional rendered image;
create a reduced triangle mesh by removing one or more triangles from the triangle mesh, wherein the one or more triangles are removed based on the camera position;
subdivide each triangle of the reduced triangle mesh into one or more subdivided triangles wherein the one or more subdivided triangles include a number of smaller triangles formed by a number of sub-edges and connecting edges divided from each triangle of the reduced triangle mesh, wherein the number of sub-edges divided from an edge of a triangle is defined by a proportion to a length of the edge;
perform a mapping of each pixel of the three-dimensional rendered image to the reduced triangle mesh;
assign a color value to each vertex of the reduced triangle mesh;
sort each triangle of the reduced triangle mesh using a depth value of each triangle; and
generate a two-dimensional triangle mesh using the sorted triangles of the reduced triangle mesh.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions for creating a reduced triangle mesh by removing one or more triangles from the triangle mesh comprises:
determining that the one or more triangles are not visible to the camera using the camera position and the three-dimensional rendered image; and
removing the one or more triangles from the triangle mesh.

11. The non-transitory computer-readable storage medium of claim 9 , wherein the connecting edge is a second sub-edge of an adjacent smaller triangle.

12. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions for assigning a color value to each vertex of the reduced triangle mesh comprises:
performing an inverse projection of the color value of a pixel of the three-dimensional rendered image to each vertex of the reduced triangle mesh;
detecting a triangle of the reduced triangle mesh that does not have an assigned color value;
identifying a nearest neighbor to the one or more triangle; and
assigning the color value of the nearest neighbor triangle to the triangle.

13. The non-transitory computer-readable storage medium of claim 12 , wherein performing an inverse projection of the color value of a pixel of the three-dimensional rendered image to each vertex of the reduced triangle mesh comprises computing a barycentric weight of each pixel for each vertex of the reduced triangle mesh.

14. The non-transitory computer-readable storage medium of claim 9 , wherein obtaining a three-dimensional rendered image comprises performing a three-dimensional rendering on a two-dimensional vector graphic.

15. The non-transitory computer-readable storage medium of claim 9 , the instructions further comprising the processor to flatten the two-dimensional triangle mesh by removing a depth value from the two-dimensional triangle mesh, wherein the flattening is performed in a primitive space.

16. A system comprising:
a processor; and
a memory including instructions which, when executed by the processor, cause the system to:
obtain a three-dimensional rendered image and a camera position;
obtain a triangle mesh representing the three-dimensional rendered image;
create a reduced triangle mesh by removing one or more triangles from the triangle mesh, wherein the one or more triangles are removed based on the camera position;
subdivide each triangle of the reduced triangle mesh into one or more subdivided triangles wherein the one or more subdivided triangles include a number of smaller triangles formed by a number of sub-edges and connecting edges divided from each triangle of the reduced triangle mesh, wherein the number of sub-edges divided from an edge of a triangle is defined by a proportion to a length of the edge;

perform a mapping of each pixel of the three-dimensional rendered image to the reduced triangle mesh;
assign a color value to each vertex of the reduced triangle mesh;
sort each triangle of the reduced triangle mesh using a depth value of each triangle; and
generate a two-dimensional triangle mesh using the sorted triangles of the reduced triangle mesh.

17. The system of claim 16 , wherein the instructions which, when executed by the processor, cause the system to create a reduced triangle mesh by removing one or more triangles from the triangle mesh, further causes the processor to:
determine that the one or more triangles are not visible to the camera using the camera position and the thre

Assignees

• Adobe Inc

Inventors

• Phogat Ankit
• Sun Xin
• Batra Vineet
• Dhingra Sumit
• Carr Nathan A
• Hasan Milos

Classifications

• G06T17/205

  Re-meshing · CPC title

• G06T11/20

  Drawing from basic elements · CPC title

• G06T17/20

  Finite element generation, e.g. wire-frame surface description, {tesselation} · CPC title

• G06T15/10 Primary

  Geometric effects · CPC title

• G06T15/04 Primary

  Texture mapping · CPC title