Methods and apparatuses for enhancing three-dimensional models from intraoral scanning

Patent metadata

Field	Value
Publication number	US-2025384632-A1
Application number	US-202519242921-A
Country	US
Kind code	A1
Filing date	Jun 18, 2025
Priority date	Jun 18, 2024
Publication date	Dec 18, 2025
Grant date	—

Abstract

Methods and apparatuses that may improve the accuracy of three-dimensional (3D) models may compare one or more geometric properties from corresponding 2D images. The 3D model (e.g., mesh model) and the 2D images may be taken from the same scan, e.g., an intraoral scan, of the subject's dentition. In some examples normals of the 3D mesh model may be compared to a normals map derived from the 2D image(s). Alternatively or additionally, these methods and apparatuses may be configured to compare a depth map generated from a 2D image to improve the 3D digital mesh model.

First claim

What is claimed is:

1 . A method, the method comprising:
accessing a three-dimensional (3D) digital mesh model of a subject's dentition; accessing one or more two-dimensional (2D) reference images corresponding to at least a region of the 3D digital mesh model; generating a surface normal map comprising target normals from the one or more 2D reference images; computing surface normals for corresponding regions of the 3D digital mesh model; comparing the surface normals from the 3D digital mesh model and the target normals from the surface normal map to determine a displacement of vertices of the 3D digital mesh to minimize the differences between the surface normals from the 3D digital mesh model and the target normals from the surface normal map; and modifying the 3D digital mesh model using the determined displacement of vertices.

2 . The method of claim 1 , wherein comparing the surface normals and the target normals comprises solving a sparse linear equation system to optimize displacement of vertices of the 3D digital mesh that minimizes a cost function representing a difference between the surface normals from the 3D digital mesh model and the target normals from the surface normal map.

3 . The method of claim 1 , wherein the surface normal map is generated using a trained machine learning model configured to estimate normals from the 2D reference images.

4 . The method of claim 1 , wherein the displacement of vertices is constrained by shared vertices of adjacent faces in the mesh.

5 . The method of claim 2 , wherein the cost function includes a regularization term based on vertex area and a weight term based on cotangent Laplacian.

6 . The method of claim 1 , wherein a direction of displacement for each vertex is defined along a vertex normal or along a ray from a virtual camera to the vertex.

7 . The method of claim 1 , further comprising dividing the 3D digital mesh model into a plurality of sub-regions and applying the method iteratively to each sub-region.

8 . The method of claim 1 , wherein the 2D reference images are obtained concurrently with or as part of an intraoral scan used to generate the 3D digital mesh model.

9 . The method of claim 1 , wherein the 3D digital mesh model includes both external and internal surfaces derived from visible and near-infrared imaging modalities.

10 . The method of claim 1 , wherein the output of the modified 3D digital mesh model is used to fabricate a dental appliance.

11 . A method, the method comprising:
accessing a three-dimensional (3D) digital mesh model of a subject's dentition; accessing one or more two-dimensional (2D) reference images corresponding to at least a region of the 3D digital mesh model; generating a surface normal map comprising target normals from the one or more 2D reference images; computing surface normals for corresponding regions of the 3D digital mesh model; determining a displacement of vertices of the 3D digital mesh that minimizes a cost function including a difference between the surface normals from the 3D digital mesh model and the target normals from the surface normal map; modifying the 3D digital mesh model using the determined displacement of vertices; and outputting the modified 3D digital mesh model.

12 . A system, the system, comprising:
an intraoral scanner configured to generate an initial three-dimensional (3D) digital mesh model of a subject's dentition; a processing unit comprising a memory storing computer-program instructions, that, when executed by the one or more processors, perform a computer-implemented method comprising:
accessing the 3D digital mesh model of the subject's dentition;
accessing one or more two-dimensional (2D) reference images corresponding to at least a region of the 3D digital mesh model;
generating a surface normal map comprising target normals from the one or more 2D reference images;
computing surface normals for corresponding regions of the 3D digital mesh model;
comparing the surface normals from the 3D digital mesh model and the target normals from the surface normal map to determine a displacement of vertices of the 3D digital mesh to minimize the differences between the surface normals from the 3D digital mesh model and the target normals from the surface normal map; and
modifying the 3D digital mesh model using the determined displacement of vertices.

13 . The system of claim 12 , wherein comparing the surface normals and the target normals comprises solving a sparse linear equation system to optimize displacement of vertices of the 3D digital mesh that minimizes a cost function representing a difference between the surface normals from the 3D digital mesh model and the target normals from the surface normal map.

14 . The system of claim 12 , wherein the surface normal map is generated using a trained machine learning model configured to estimate normals from the 2D reference images.

15 . The system of claim 12 , wherein the displacement of vertices is constrained by shared vertices of adjacent faces in the mesh.

16 . The system of claim 15 , wherein the cost function includes a regularization term based on vertex area and a weight term based on cotangent Laplacian.

17 . The system of claim 12 , wherein a direction of displacement for each vertex is defined along a vertex normal or along a ray from a virtual camera to the vertex.

18 . The system of claim 12 , further comprising dividing the 3D digital mesh model into a plurality of sub-regions and applying the method iteratively to each sub-region.

19 . The system of claim 12 , wherein the 2D reference images are obtained concurrently with or as part of an intraoral scan used to generate the 3D digital mesh model.

20 . The system of claim 12 , wherein the 3D digital mesh model includes both external and internal surfaces derived from visible and near-infrared imaging modalities.

Assignees

• Align Technology Inc

Inventors

• Moshe Maayan
• Peleg Gal
• Lellouch Michael

Classifications

• G06T2210/41

  Medical · CPC title

• G06T2207/30036

  Dental; Teeth · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20021

  Dividing image into blocks, subimages or windows · CPC title

• G06T2207/10048

  Infrared image · CPC title