Invention Application
- Patent Title: SURFACE GEOMETRY OBJECT MODEL TRAINING AND INFERENCE
-
Application No.: US16591359Application Date: 2019-10-02
-
Publication No.: US20210104096A1Publication Date: 2021-04-08
- Inventor: Artsiom Ablavatski , Yury Kartynnik , Ivan Grishchenko , Matthias Grundmann
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Main IPC: G06T17/20
- IPC: G06T17/20 ; G06N3/08

Abstract:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network model to predict mesh vertices corresponding to a three-dimensional surface geometry of an object depicted in an image.
Public/Granted literature
- US11158122B2 Surface geometry object model training and inference Public/Granted day:2021-10-26
Information query