Back to results
US 12,592,032 B2Granted
Unlocking lightweight fast 3D visualization with neural radiance representations
AssigneeSchlumberger Technology Corporation
InventorsSalma Benslimane, Prasham Sheth, Kishore Mulchandani, Vineet Kamboj, Crispin Chatar
Life of this patent
Estimating the term…
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.
Claims20
A method of visualization, comprising:
- receiving a plurality of two-dimensional images associated with wellsite production equipment, wherein each of the plurality of two-dimensional images comprises at least one object corresponding to the wellsite production equipment;
- determining a camera position relative to the at least one object in each of the plurality of two-dimensional images;
- determining a camera angle relative to the at least one object in each of the plurality of two-dimensional images;
- generating a file for each of the plurality of two-dimensional images based on the camera position and the camera angle, wherein each file comprises structured information corresponding to the camera position and the camera angle in each of the plurality of two-dimensional images;
- generating a three-dimensional representation of the at least one object based on providing the file for each of the plurality of two-dimensional images to a neural radiance field (NeRF) model, wherein the three-dimensional representation is a novel view of the at least one object with respect to each view of the at least one object in each of the plurality of two-dimensional images;
- rendering the three-dimensional representation of the at least one object;
- receiving a historical three-dimensional representation of the at least one object previously generated by the NeRF model, wherein the historical three-dimensional representation is generated based on one or more previous NeRF captures of the at least one object over a period of time;
- and
- determining an indication of use of the at least one object based on a comparison between the three-dimensional representation of the at least one object and the historical three-dimensional representation of the at least one object, wherein the indication of use comprises a number of times the at least one object has been interacted with, a duration of the interaction with the at least one object, or both.
6 more elements
A system for visualization, comprising:
- a device for capturing a plurality of two-dimensional images of wellsite production equipment, wherein each of the plurality of two-dimensional images comprises at least one object corresponding to the wellsite production equipment;
- and
- a surface unit comprising a computer system having a computer processor configured to:
- receive the plurality of two-dimensional images from the device;
- determine a camera position relative to the at least one object in each of the plurality of two-dimensional images;
- determine a camera angle relative to the at least one object in each of the plurality of two-dimensional images;
- generate a file for each of the plurality of two-dimensional images acquired by the device based on the camera position and the camera angle, wherein each file comprises structured information corresponding to the camera position and the camera angle in each of the plurality of two-dimensional images;
- generate a three-dimensional representation of the at least one object based on providing the file for each of the plurality of two-dimensional images to a neural radiance field (NeRF) model, wherein the three-dimensional representation is a novel view of the at least one object with respect to each view of the at least one object in each of the plurality of two-dimensional images;
- render the three-dimensional representation of the at least one object;
- receive a historical three-dimensional representation of the at least one object previously generated by the NeRF model, wherein the historical three-dimensional representation is generated based on one or more previous NeRF captures of the at least one object over a period of time;
- and
- determine an indication of use of the at least one object based on a comparison between the three-dimensional representation of the at least one object and the historical three-dimensional representation of the at least one object, wherein the indication of use comprises a number of times the at least one object has been interacted with, a duration of the interaction with the at least one object, or both.
9 more elements
A non-transitory, computer-readable medium, comprising computer readable program code that, when executed by one or more processors of a computer system, causes the computer system to perform operations comprising:
- receiving a plurality of two-dimensional images associated with wellsite production equipment, wherein each of the plurality of two-dimensional images comprises at least one object corresponding to the wellsite production equipment;
- determining a camera position relative to the at least one object in each of the plurality of two-dimensional images;
- determining a camera angle relative to the at least one object in each of the plurality of two-dimensional images;
- generating a file for each of the plurality of two-dimensional images based on the camera position and the camera angle, wherein each file comprises structured information corresponding to the camera position and the camera angle in each of the plurality of two-dimensional images;
- generating a three-dimensional representation of the at least one object based on providing the file for each of the plurality of two-dimensional images to a neural radiance field (NeRF) model, wherein the three-dimensional representation is a novel view of the at least one object with respect to each view of the at least one object in each of the plurality of two-dimensional images;
- rendering the three-dimensional representation of the at least one object;
- receiving a historical three-dimensional representation of the at least one object previously generated by the NeRF model, wherein the historical three-dimensional representation is generated based on one or more previous NeRF captures of the at least one object over a period of time;
- and
- determining an indication of use of the at least one object based on a comparison between the three-dimensional representation of the at least one object and the historical three-dimensional representation of the at least one object, wherein the indication of use comprises a number of times the at least one object has been interacted with, a duration of the interaction with the at least one object, or both.
6 more elements
Dependencies are inferred from the claim text.