# US 2024/0203050 A1 · Unlocking lightweight fast 3d visualization with neural radiance representations

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

- Number: US 2024/0203050 A1
- Document ID: US20240203050A1
- Status: Published application
- Kind: A1
- Application number: 18/541,585
- Filed: 2023-12-15
- Published: 2024-06-20
- Earliest claimed: 2022-12-15
- Assignees: Schlumber Technology Corporation
- Applicants: Schlumber Technology Corporation
- Inventors: Salma Benslimane; Prasham Sheth; Kishore Mulchandani; Vineet Kamboj; Crispin Chatar
- Web page: https://patentgrep.com/patent/US20240203050A1

## CPC

- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 11/00: Two-dimensional [2D] image generation
- G06T 15/08: Volume rendering
- G06T 15/20: Perspective computation
- G01V 1/345: {Visualisation of seismic data or attributes, e.g. in 3D cubes}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)

## Abstract

The description is directed to a method of visualization, involving capturing a multitude of two-dimensional images, generating transforms for each of the multitude of two-dimensional images, generating a three-dimensional representation of an object or scene based on the transforms, where the three-dimensional representation is a novel view, and rendering the three-dimensional representation of the object or scene.

## Claims

### Claim 1

A method of visualization, comprising:
capturing a plurality of two-dimensional images;
generating transforms for each of the plurality of two-dimensional images;
generating a three-dimensional representation of an object or scene based on the transforms, wherein the three-dimensional representation is a novel view; and
rendering the three-dimensional representation of the object or scene.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
performing anomaly detection using the three-dimensional representation.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
running neural radiance field (NeRF) algorithm on the transforms.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
obtaining previous NeRF captures of the object or scene; and
performing change detection using the three-dimensional representation and the previous NeRF captures.

### Claim 5 (depends on 3)

The method of claim 3, further comprising:
obtaining history of NeRF captures of the object or scene; and
monitoring equipment using the three-dimensional representation and the history of NeRF captures.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
performing segmentation and object detection using the three-dimensional representation.

### Claim 7 (depends on 1)

The method of claim 1, wherein rendering the three-dimensional representation is a visual digital twin of the object or scene.

### Claim 8 (depends on 1)

The method of claim 1, wherein the plurality of two-dimensional images is captured by a handheld RGB camera.

### Claim 9 (depends on 1)

The method of claim 1, wherein the plurality of two-dimensional images is captured by one or more sensors.

### Claim 10

A system for visualization, comprising:
a device for capturing a plurality of two-dimensional images; and
a surface unit comprising a computer system having a computer processor configured to:
generate transforms for each of the plurality of two-dimensional images acquired by the device;
generate a three-dimensional representation of an object or scene based on the transforms, wherein the three-dimensional representation is a novel view; and
render the three-dimensional representation of the object or scene.

### Claim 11 (depends on 10)

The system of claim 10, wherein the surface unit comprises the computer system having the computer processor configured to:
perform anomaly detection using the three-dimensional representation.

### Claim 12 (depends on 10)

The system of claim 10, wherein the surface unit comprises the computer system having the computer processor configured to:
run neural radiance field (NeRF) algorithm on the transforms.

### Claim 13 (depends on 12)

The system of claim 12, wherein the surface unit comprises the computer system having the computer processor configured to:
obtain previous NeRF captures of the object or scene; and
perform change detection using the three-dimensional representation and the previous NeRF captures.

### Claim 14 (depends on 12)

The system of claim 12, wherein the surface unit comprises the computer system having the computer processor configured to:
obtain history of NeRF captures of the object or scene; and
monitor equipment using the three-dimensional representation and the history of NeRF captures.

### Claim 15 (depends on 10)

The system of claim 10, wherein the surface unit comprises the computer system having the computer processor configured to:
perform segmentation and object detection using the three-dimensional representation.

### Claim 16 (depends on 10)

The system of claim 10, wherein rendering the three-dimensional representation is a visual digital twin of the object or scene.

### Claim 17 (depends on 10)

The system of claim 10, wherein the plurality of two-dimensional images is captured by a handheld RGB camera.

### Claim 18 (depends on 10)

The system of claim 10, wherein the plurality of two-dimensional images is captured by a one or more sensors.

### Claim 19

A computer program product comprising computer readable program code for causing a computer system to perform operations comprising:
capturing a plurality of two-dimensional images;
generating transforms for each of the plurality of two-dimensional images;
generating a three-dimensional representation of an object or scene based on the transforms, wherein the three-dimensional representation is a novel view; and
rendering the three-dimensional representation of the object or scene.

### Claim 20 (depends on 19)

The computer program product of claim 19, further comprising computer readable program code for causing a computer system to perform operations comprising:
running neural radiance field (NeRF) algorithm on the transforms.
