View source for Google llc (20240119697). Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes simplified abstract

=Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes=


==Organization Name==

[[:Category:google llc|google llc]]


[[Category:google llc]]

==Inventor(s)==

[[:Category:Daniel Christopher Duckworth of Berlin (DE)|Daniel Christopher Duckworth of Berlin (DE)]][[Category:Daniel Christopher Duckworth of Berlin (DE)]]

[[:Category:Suhani Deepak-Ranu Vora of San Mateo CA (US)|Suhani Deepak-Ranu Vora of San Mateo CA (US)]][[Category:Suhani Deepak-Ranu Vora of San Mateo CA (US)]]

[[:Category:Noha Radwan of Zurich (CH)|Noha Radwan of Zurich (CH)]][[Category:Noha Radwan of Zurich (CH)]]

[[:Category:Klaus Greff of Berlin (DE)|Klaus Greff of Berlin (DE)]][[Category:Klaus Greff of Berlin (DE)]]

[[:Category:Henning Meyer of Berlin (DE)|Henning Meyer of Berlin (DE)]][[Category:Henning Meyer of Berlin (DE)]]

[[:Category:Kyle Adam Genova of San Mateo CA (US)|Kyle Adam Genova of San Mateo CA (US)]][[Category:Kyle Adam Genova of San Mateo CA (US)]]

[[:Category:Seyed Mohammad Mehdi Sajjadi of Berlin (DE)|Seyed Mohammad Mehdi Sajjadi of Berlin (DE)]][[Category:Seyed Mohammad Mehdi Sajjadi of Berlin (DE)]]

[[:Category:Etienne François Régis Pot of Berlin (DE)|Etienne François Régis Pot of Berlin (DE)]][[Category:Etienne François Régis Pot of Berlin (DE)]]

[[:Category:Andrea Tagliasacchi of Victoria (CA)|Andrea Tagliasacchi of Victoria (CA)]][[Category:Andrea Tagliasacchi of Victoria (CA)]]

==Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240119697 titled 'Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes

==Simplified Explanation==

The abstract describes a computer-implemented method for constructing a three-dimensional semantic segmentation of a scene from two-dimensional inputs.

* Obtaining an image set of one or more views of a subject scene.
* Generating a scene representation in three dimensions based on the image set.
* Generating a multidimensional field of probability distributions over semantic categories using a machine-learned semantic segmentation model framework.
* Outputting classification data for at least one location in the subject scene.

== Potential Applications ==
This technology could be applied in various fields such as autonomous driving, robotics, augmented reality, and virtual reality for scene understanding and object recognition.

== Problems Solved ==
This technology solves the problem of accurately segmenting and understanding a scene in three dimensions from two-dimensional inputs, which can be challenging for computer vision systems.

== Benefits ==
The benefits of this technology include improved scene understanding, accurate object recognition, and enhanced decision-making capabilities for autonomous systems.

== Potential Commercial Applications ==
Potential commercial applications of this technology include autonomous vehicles, surveillance systems, augmented reality applications, and robotics for various industries.

== Possible Prior Art ==
One possible prior art for this technology could be the use of machine learning models for semantic segmentation in computer vision applications.

== Unanswered Questions ==
1. How does this technology handle complex scenes with multiple objects and occlusions?
2. What are the limitations of this method in terms of scalability and real-time processing?


==Original Abstract Submitted==

example embodiments of the present disclosure provide an example computer-implemented method for constructing a three-dimensional semantic segmentation of a scene from two-dimensional inputs. the example method includes obtaining, by a computing system comprising one or more processors, an image set comprising one or more views of a subject scene. the example method includes generating, by the computing system and based at least in part on the image set, a scene representation describing the subject scene in three dimensions. the example method includes generating, by the computing system and using a machine-learned semantic segmentation model framework, a multidimensional field of probability distributions over semantic categories, the multidimensional field defined over the three dimensions of the subject scene. the example method includes outputting, by the computing system, classification data for at least one location in the subject scene.



[[Category:G06V10/26]]
[[Category:G06T7/143]]
[[Category:G06T15/08]]