Vivek Verma

US Patent:

20220270314, Aug 25, 2022

Filed:

Feb 22, 2022

Appl. No.:

17/677123

Inventors:

- San Mateo CA, US
Dario KNEUBUHLER - Zurich, CH
Tijmen VERHULSDONCK - Göteborg, SE
Eloi DU BOIS - Austin TX, US
Will WELCH - San Francisco CA, US
Vivek VERMA - Oakland CA, US
Ian SACHS - Corte Madera CA, US
Kiran BHAT - San Francisco CA, US

Assignee:

Roblox Corporation - San Mateo CA

International Classification:

G06T 13/40
G06T 7/73
G06V 40/16
G06V 10/82
G06V 10/774
G06V 10/24

Abstract:

Implementations described herein relate to methods, systems, and computer-readable media to generate animations for a 3D avatar from input video captured at a client device. A camera may capture video of a face while a trained face detection model and a trained regression model output a set of FACS weights, head poses, and facial landmarks to be translated into the animations of the 3D avatar. Additionally, a higher level-of-detail may be intelligently selected based upon user preferences and/or computing conditions at the client device.

US Patent:

20210027511, Jan 28, 2021

Filed:

Jul 23, 2020

Appl. No.:

16/937355

Inventors:

- San Francisco CA, US
Eloi Henri Homere Du Bois - Austin TX, US
Inaki Navarro - San Francisco CA, US
Will Welch - San Francisco CA, US
Rishabh Battulwar - Redwood City CA, US
Ian Sachs - Corte Madera CA, US
Vivek Verma - Oakland CA, US
Kiran Bhat - San Francisco CA, US

Assignee:

LoomAi, Inc. - San Francisco CA

International Classification:

G06T 13/20
G06T 13/40
G06T 15/50
G10L 25/24
G06N 3/08
G06N 3/04

Abstract:

Systems and methods for animating from audio in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating animation from audio. The method includes steps for receiving input audio data, generating an embedding for the input audio data, and generating several predictions for several tasks from the generated embedding. The several predictions includes at least one of blendshape weights, event detection, and/or voice activity detection. The method includes steps for generating a final prediction from the several predictions, where the final prediction includes a set of blendshape weights, and generating an output based on the generated final prediction.