Jump to content

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

From WikiPatents
Revision as of 17:42, 10 May 2025 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)


HUMAN SUBJECT GAUSSIAN SPLATTING USING MACHINE LEARNING

Organization Name

Apple Inc.

Inventor(s)

Anurag Ranjan of Sunnyvale CA US

Muhammed Kocabas of Seattle WA US

James C. Gabriel of Seattle WA US

Jen-Hao Chang of Santa Clara CA US

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.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.