View source for 18653917. HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING (Apple Inc.)

<!-- JSON-LD markup for search engines:
{"@context":"https://schema.org","@type":"TechArticle","headline":"HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING","name":"HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING","description":"Aspects of the subject technology provide for human subject Gaussian splatting using machine learning. A method includes receiving a video input having a scene and a subject. The method also includes ...","datePublished":"2024-05-02","mainEntity":{"@type":"Patent","identifier":"18653917","name":"HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING","abstract":"Aspects of the subject technology provide for human subject Gaussian splatting using machine learning. A method includes receiving a video input having a scene and a subject. The method also includes obtaining a three-dimensional (3D) reconstruction of the subject and the scene from the video input. The method includes generating a 3D Gaussian representation of each of the scene and the subject. The method also includes generating a deformed 3D Gaussian representation of the subject by adapting the 3D Gaussian representation of the subject to the 3D reconstruction of the subject. The method includes rendering a visual output comprising an animatable avatar of the subject and the scene using differentiable Gaussian rasterization based at least in part on the deformed 3D Gaussian representation of the subject and the 3D Gaussian representation of the scene.","applicationNumber":"18653917","datePublished":"2024-05-02","inventor":[{"@type":"Person","name":"Anurag RANJAN"},{"@type":"Person","name":"Muhammed KOCABAS"},{"@type":"Person","name":"James C. GABRIEL"},{"@type":"Person","name":"Jen-Hao CHANG"},{"@type":"Person","name":"Cuneyt O. TUZEL"}],"applicant":{"@type":"Organization","name":"Apple Inc."},"additionalProperty":[{"@type":"PropertyValue","name":"IPC Classification","value":"G06T13/40"},{"@type":"PropertyValue","name":"IPC Classification","value":"G06T7/579"},{"@type":"PropertyValue","name":"IPC Classification","value":"G06T7/70"},{"@type":"PropertyValue","name":"IPC Classification","value":"G06T17/20"},{"@type":"PropertyValue","name":"CPC Classification","value":"G06T13/40"}]}}
-->

=HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING=


==Organization Name==

[[:Category:Apple Inc.|Apple Inc.]]


[[Category:Apple Inc.]]

==Inventor(s)==

[[:Category:Anurag Ranjan of Sunnyvale CA US|Anurag Ranjan of Sunnyvale CA US]][[Category:Anurag Ranjan of Sunnyvale CA US]]

[[:Category:Muhammed Kocabas of Seattle WA US|Muhammed Kocabas of Seattle WA US]][[Category:Muhammed Kocabas of Seattle WA US]]

[[:Category:James C. Gabriel of Seattle WA US|James C. Gabriel of Seattle WA US]][[Category:James C. Gabriel of Seattle WA US]]

[[:Category:Jen-Hao Chang of Santa Clara CA US|Jen-Hao Chang of Santa Clara CA US]][[Category:Jen-Hao Chang of Santa Clara CA US]]

[[:Category:Cuneyt O. Tuzel of Cupertino CA US|Cuneyt O. Tuzel of Cupertino CA US]][[Category:Cuneyt O. Tuzel of Cupertino CA US]]

==HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING==


This abstract first appeared for US patent application 18653917 titled 'HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING

==Original Abstract Submitted==

Aspects of the subject technology provide for human subject Gaussian splatting using machine learning. A method includes receiving a video input having a scene and a subject. The method also includes obtaining a three-dimensional (3D) reconstruction of the subject and the scene from the video input. The method includes generating a 3D Gaussian representation of each of the scene and the subject. The method also includes generating a deformed 3D Gaussian representation of the subject by adapting the 3D Gaussian representation of the subject to the 3D reconstruction of the subject. The method includes rendering a visual output comprising an animatable avatar of the subject and the scene using differentiable Gaussian rasterization based at least in part on the deformed 3D Gaussian representation of the subject and the 3D Gaussian representation of the scene.



[[Category:G06T13/40]]
[[Category:G06T7/579]]
[[Category:G06T7/70]]
[[Category:G06T17/20]]
[[Category:CPC_G06T13/40]]