Synthesizing high resolution 3d shapes from lower resolution representations for synthetic data generation systems and applications
US-2022392162-A1 · Dec 8, 2022 · US
US11830145B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11830145-B2 |
| Application number | US-202117479866-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 20, 2021 |
| Priority date | Sep 20, 2021 |
| Publication date | Nov 28, 2023 |
| Grant date | Nov 28, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A manifold voxel mesh or surface mesh is manufacturable by carving a single block of material and a non-manifold mesh is not manufacturable. Conventional techniques for constructing or extracting a surface mesh from an input point cloud often produce a non-manifold voxel mesh. Similarly, extracting a surface mesh from a voxel mesh that includes non-manifold geometry produces a surface mesh that includes non-manifold geometry. To ensure that the surface mesh includes only manifold geometry, locations of the non-manifold geometry in the voxel mesh are detected and converted into manifold geometry. The result is a manifold voxel mesh from which a manifold surface mesh of the object may be extracted.
Opening claim text (preview).
What is claimed is: 1. A computer-implemented method, comprising: receiving a non-manifold voxel mesh model of an object; identifying a location in the non-manifold voxel mesh model of non-manifold geometry, wherein identifying comprises performing a convolution operation by applying a three-dimensional (3D) kernel of pattern mask values to each voxel in the non-manifold voxel mesh model; inserting an additional voxel into the voxel mesh model at the location to convert the non-manifold voxel mesh model into a modified voxel mesh model; and extracting a manifold surface mesh of the object from the modified voxel mesh model. 2. The computer-implemented method of claim 1 , wherein the non-manifold geometry is a non-manifold vertex. 3. The computer-implemented method of claim 1 , wherein identifying further comprises performing the convolution operation by applying rotated versions of the 3D kernel to each voxel in the non-manifold voxel mesh model. 4. The computer-implemented method of claim 3 , wherein the 3D kernel is centered on the voxel and comprises the pattern mask values of [ 0 0 0 0 0 0 0 0 0 ] , [ - 1 - 1 0 - 1 0 0 0 0 0 ] , [ 6 - 1 0 - 1 - 1 0 0 0 0 ] . 5. The computer-implemented method of claim 3 , wherein the 3D kernel is centered on the voxel and comprises the pattern mask values of [ 0 0 0 0 0 0 0 0 0 ] , [ - 1 - 1 0 1 0 0 0 0 0 ] , [ - 1 1 0 - 1 - 1 0 0 0 0 ] . 6. The computer-implemented method of claim 1 , wherein the non-manifold geometry is a no
Re-meshing · CPC title
Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title
Learning methods · CPC title
Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts · CPC title
Data acquisition or data processing for additive manufacturing · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.