# US 2024/0203020 A1 · Systems and methods for generating or rendering a three-dimensional representation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0203020 A1
- Document ID: US20240203020A1
- Status: Published application
- Kind: A1
- Application number: 18/555,724
- Filed: 2022-04-12
- Published: 2024-06-20
- Earliest claimed: 2021-04-16
- Assignees: Hover Inc.
- Applicants: Hover Inc.
- Inventors: Matthew THOMAS; Harsh BARBHAIYA; Jeffrey SOMMERS
- Web page: https://patentgrep.com/patent/US20240203020A1

## CPC

- G06T 15/00: Three-dimensional [3D] image rendering
- G06T 15/20: Perspective computation
- G06T 7/174: involving the use of two or more images
- G06T 7/74: {involving reference images or patches}
- G06T 11/00: Two-dimensional [2D] image generation
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/30244: Camera pose
- G06T 2210/56: Particle system, point based geometry or rendering
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems and methods for generating or rendering a three-dimensional (3D) representation of a structure based on images of the structure are disclosed. A selectively rendered point cloud is generated based on the images of the structure and real cameras associated with a virtual camera observing the selectively rendered point cloud. Images attributes may be applied to the selectively rendered point cloud.

## Claims

### Claim at position 1

-204. (canceled)

### Claim 205

A method for generating a three-dimensional (3D) representation, the method comprising:
receiving a plurality of images associated with a plurality of real cameras;
generating a point cloud based on the plurality of images, wherein the point cloud comprises a plurality of points;
selecting real cameras associated with a virtual camera, wherein the selected real cameras comprise a subset of the plurality of real cameras; and
generating a 3D representation comprising a subset of the plurality of points of the point cloud from a perspective of the virtual camera based on a relation of the virtual camera to the selected real cameras.

### Claim 206 (depends on 205)

The method of claim 205, wherein the point cloud is a line cloud.

### Claim 207 (depends on 205)

The method of claim 205, further comprising:
segmenting the point cloud based on a subject of interest in the plurality of images,
wherein the 3D representation comprises a subset of a plurality of points of the segmented point cloud.

### Claim 208 (depends on 205)

The method of claim 205, further comprising:
segmenting each image of the plurality of images based on a subject of interest in the plurality of images,
wherein generating the point cloud is based on the plurality of segmented images.

### Claim 209 (depends on 205)

The method of claim 205, further comprising:
selecting the virtual camera within a spatial constraint, wherein the spatial constraint is established based on the plurality of real cameras.

### Claim 210 (depends on 205)

The method of claim 205, wherein selecting the real cameras associated with the virtual camera comprises:
comparing a pose of each real camera of the plurality of real cameras to a pose of the virtual camera; and
selecting a real camera of the plurality of real cameras responsive to a distance between a pose of the real camera and the pose of the virtual camera being less than a threshold distance value.

### Claim 211 (depends on 205)

The method of claim 205, wherein selecting the real cameras associated with the virtual camera comprises selecting real cameras of the plurality of real cameras that are nearest neighbors of the virtual camera.

### Claim 212 (depends on 205)

The method of claim 205, wherein selecting the real cameras associated with the virtual camera comprises:
comparing a field of view of each real camera of the plurality of real cameras to a field of view of the virtual camera; and
selecting a real camera of the plurality of real cameras responsive to the field of view of the real camera overlapping the field of view of the virtual camera.

### Claim 213 (depends on 205)

The method of claim 205, wherein selecting the real cameras associated with the virtual camera comprises:
comparing capture times associated with the real cameras of the plurality of real cameras to one another; and
selecting real cameras of the plurality of real cameras responsive to the real cameras being temporally proximate to one another.

### Claim 214 (depends on 205)

The method of claim 205, wherein generating the 3D representation comprising the subset of the plurality of points of the point cloud from the perspective of the virtual camera comprises:
selecting points of the plurality of points of the point cloud that were observed by the selected real cameras associated with the virtual camera,
wherein the subset of the plurality of points of the point cloud comprises the selected points.

### Claim 215 (depends on 205)

The method of claim 205, further comprising:
generating a two-dimensional (2D) representation of the 3D representation from the perspective of the virtual camera.

### Claim 216 (depends on 205)

The method of claim 205, wherein generating the 3D representation comprising the subset of the plurality of points of the point cloud from the perspective of the virtual camera comprises generating a color value for each point of the subset of the plurality of points.

### Claim 217 (depends on 216)

The method of claim 216, wherein generating the color value for each point of the subset of the plurality of points comprises selecting a predominant color value of pixel color values according to the images that were used to triangulate the point.

### Claim 218

One or more non-transitory computer-readable media storing one or more sequences of instructions that, when executed by one or more processors, cause:
receiving a plurality of images associated with a plurality of real cameras;
generating a point cloud based on the plurality of images, wherein the point cloud comprises a plurality of points;
selecting real cameras associated with a virtual camera, wherein the selected real cameras comprise a subset of the plurality of real cameras; and
generating a 3D representation comprising a subset of the plurality of points of the point cloud from a perspective of the virtual camera based on a relation of the virtual camera to the selected real cameras.

### Claim 219

A method for generating a three-dimensional (3D) representation, the method comprising:
receiving a plurality of images associated with a plurality of real cameras;
generating a point cloud based on the plurality of images, wherein the point cloud comprises a plurality of points;
selecting points of the point cloud associated with a virtual camera, wherein the selected points comprise a subset of the plurality of points; and
generating a 3D representation comprising the selected points from a perspective of the virtual camera based on a relation of the virtual camera to the selected points.

### Claim 220

A method for generating a three-dimensional (3D) representation, the method comprising:
receiving a plurality of images associated with a plurality of real cameras;
generating a point cloud based on the plurality of images, wherein the point cloud comprises a plurality of points;
calculating distances between the plurality of real cameras and a virtual camera; and
generating a three-dimensional (3D) representation comprising a subset of the plurality of points of the point cloud from a perspective of the virtual camera based on the distances between the plurality of real cameras and the virtual camera.

### Claim 221

A method for rendering points, the method comprising:
receiving a plurality of images associated with a plurality of real cameras;
generating a point cloud based on the plurality of images, wherein the point cloud comprises a plurality of points;
selecting first real cameras associated with a first virtual camera, wherein the first real cameras comprise a first subset of the plurality of real cameras;
selecting second real cameras associated with a second virtual camera, wherein the second real cameras comprise a second subset of the plurality of real cameras;
selecting a first plurality of points of the point cloud based on a first relation of the first virtual camera to the first real cameras;
selecting a second plurality of points of the point cloud based on a second relation of the second virtual camera to the second real cameras; and
rendering the first plurality of points and the second plurality of points based on a transition from the first virtual camera to the second virtual camera.

### Claim 222

A method for generating a path of a virtual camera, the method comprising:
receiving a plurality of images;
for each image of the plurality of images, calculating a pose of a real camera associated with the image; and
generating a path of a virtual camera based on the calculated poses of the real cameras.
