Accurate smooth occluding contours

US11941746B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-11941746-B2
Application numberUS-202117466670-A
CountryUS
Kind codeB2
Filing dateSep 3, 2021
Priority dateSep 3, 2021
Publication dateMar 26, 2024
Grant dateMar 26, 2024

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Embodiments are disclosed for computing accurate smooth occluding contours. In one embodiment, a method of computing accurate smooth occluding contours includes projecting a boundary polygon associated with a first region of a three-dimensional (3D) object to a two-dimensional (2D) image plane, the boundary polygon comprising a plurality of contour vertices and edges connecting the plurality of contour vertices, triangulating the first region in the 2D image plane to generate a 2D triangulation, and generating a 3D mesh for the first region by mapping the 2D triangulation to the 3D object.

First claim

Opening claim text (preview).

We claim: 1. A computer-implemented method comprising: projecting a boundary polygon associated with a first region of a three-dimensional (3D) object to a two-dimensional (2D) image plane, the boundary polygon comprising a plurality of contour vertices and edges connecting the plurality of contour vertices; triangulating the first region in the 2D image plane to generate a 2D triangulation; and generating a 3D mesh for the first region by mapping the 2D triangulation to the 3D object by connecting at least one pair of contour vertices with a path on a surface of the 3D object which corresponds to a straight line connection in the 2D image plane, and refining the 2D triangulation based on sample points collected along the path on the surface of the 3D object. 2. The computer-implemented method of claim 1 , further comprising: iteratively generating a 3D mesh for each remaining region of the 3D object by: projecting a boundary polygon associated with that region to the 2D image plane; triangulating that region in the 2D image plane to generate a 2D triangulation; and mapping the 2D triangulation for that region to the 3D object. 3. The computer-implemented method of claim 2 , further comprising: generating an output mesh by combining each 3D mesh corresponding to each region. 4. The computer-implemented method of claim 3 , further comprising: providing the output mesh to a mesh contour detection and stylization system, wherein the mesh contour detection and stylization system generates a stylized line drawing based on the output mesh and a user-indicated style; and causing the stylized line drawing to be returned to a user. 5. The computer-implemented method of claim 3 , further comprising: providing the output mesh to a mesh contour detection and stylization system, wherein the mesh contour detection and stylization system generates a vector graphics object corresponding to an occluding contour of the output mesh; and causing the vector graphics object to be returned to a user. 6. The computer-implemented method of claim 1 , wherein generating a 3D mesh for the first region by mapping the 2D triangulation to the 3D object, further comprises: selecting a first contour vertex and a second contour vertex; identifying the path connecting on the 3D object connecting the first contour vertex to the second contour vertex; generating sample points along the path on the 3D object; and generating a refined 2D triangulation using the contour vertices and the sample points. 7. The computer-implemented method of claim 6 , wherein generating sample points along the path on the 3D object, further comprises: adding the sample points that were generated on the path in a direction of travel from the first contour vertex to the second contour vertex; and discarding the sample points that were generated on the path in a direction of travel from the second contour vertex to the first contour vertex. 8. The computer-implemented method of claim 1 , wherein the 3D object is a self-overlapping object, a weakly self-overlapping object, or a weakly self-overlapping object with one or more holes. 9. The computer-implemented method of claim 1 , further comprising: receiving a request to generate occluding contours for the 3D object, the request including the 3D object and a viewpoint; inserting contour vertices into an initial mesh of the 3D object, the contour vertices corresponding to at least one occluding contour on the 3D object; and partitioning the 3D object into a plurality of regions based at least on the contour vertices. 10. 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: project a boundary polygon associated with a first region of a three-dimensional (3D) object to a two-dimensional (2D) image plane, the boundary polygon comprising a plurality of contour vertices and edges connecting the plurality of contour vertices; triangulate the first region in the 2D image plane to generate a 2D triangulation; and generate a 3D mesh for the first region by mapping the 2D triangulation to the 3D object by connecting at least one pair of contour vertices with a path on a surface of the 3D object which corresponds to a straight line connection in the 2D image plane, and refining the 2D triangulation based on sample points collected along the path on the surface of the 3D object. 11. The non-transitory computer-readable storage medium of claim 10 , wherein the instructions, when executed, further cause the at least one processor to: iteratively generate a 3D mesh for each remaining region of the 3D object by: projecting a boundary polygon associated with that region to the 2D image plane; triangulating that region in the 2D image plane to generate a 2D triangulation; and mapping the 2D triangulation for that region to the 3D object. 12. The non-transitory computer-readable storage medium of claim 11 , wherein the instructions, when executed, further cause the at least one processor to: generate an output mesh by combining each 3D mesh corresponding to each region. 13. The non-transitory computer-readable storage medium of claim 12 , wherein the instructions, when executed, further cause the at least one processor to: provide the output mesh to a mesh contour detection and stylization system, wherein the mesh contour detection and stylization system generates a stylized line drawing based on the output mesh and a user-indicated style; and cause the stylized line drawing to be returned to a user. 14. The non-transitory computer-readable storage medium of claim 12 , wherein the instructions, when executed, further cause the at least one processor to: provide the output mesh to a mesh contour detection and stylization system, wherein the mesh contour detection and stylization system generates a vector graphics object corresponding to an occluding contour of the output mesh; and cause the vector graphics object. 15. The non-transitory computer-readable storage medium of claim 10 , wherein to generate a 3D mesh for the first region by mapping the 2D triangulation to the 3D object, the instructions, when executed, further cause the at least one processor to: select a first contour vertex and a second contour vertex; identify a path connecting on the 3D object connecting the first contour vertex to the second contour vertex; generate sample points along the path on the 3D object; and generate a refined 2D triangulation using the contour vertices and the sample points. 16. The non-transitory computer-readable storage medium of claim 15 , wherein to generate sample points along the path on the 3D object, the instructions, when executed, further cause the at least one processor to: add the sample points that were generated on the path in a direction of travel from the first contour vertex to the second contour vertex; and discard the sample points that were generated on the path in a direction of travel from the second contour vertex to the first contour vertex. 17. The non-transitory computer-readable storage medium of claim 10 , wherein the 3D object is a self-overlapping object, a weakly self-overlapping object, or a weakly self-overlapping object with one or more holes. 18. The non-transitory computer-readable storage medium of claim 10 , wherein the instructions, when executed, further cause the at least one processor to: receive a request to generate occluding contours for the 3D object, the request inclu

Assignees

Inventors

Classifications

  • G06T15/20Primary

    Perspective computation · CPC title

  • G06T7/564Primary

    from contours · CPC title

  • Re-meshing · CPC title

  • involving all processing steps from image acquisition to 3D model generation · CPC title

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

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US11941746B2 cover?
Embodiments are disclosed for computing accurate smooth occluding contours. In one embodiment, a method of computing accurate smooth occluding contours includes projecting a boundary polygon associated with a first region of a three-dimensional (3D) object to a two-dimensional (2D) image plane, the boundary polygon comprising a plurality of contour vertices and edges connecting the plurality of…
Who is the assignee on this patent?
Adobe Inc
What technology area does this patent fall under?
Primary CPC classification G06T15/20. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Mar 26 2024 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 2 related publications on this page (citations in our corpus or others sharing the same primary CPC).