METHOD TO PRODUCE 3D MODEL FROM ONE OR SEVERAL IMAGES

Patent №

US 10,891,789

Granted

2021-01-12

Filed 2019

Owner

ITSEEZ3D, INC.

Lab

AI components

3

ml · vision · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16426127

The present invention provides a method to produce a 3D model of a person or an object from just one or several image. The method uses a neural network that is trained on pairs of 3D models of human heads and their frontal images, and then, given an image, infers a 3D model.

Machine learningVisionAI hardwareG06T 1/20G06F 18/2413G06N 3/0464G06N 3/08G06N 3/09G06T 3/02G06T 15/04G06T 17/00+6 more

AI classification

Vision1.00
Machine learning1.00
AI hardware0.68
Planning0.48
Speech0.00
Evolutionary computation0.00
Knowledge representation0.00
Natural language0.00

Ownership

ITSEEZ3D, INC.

assignment · 494300209

Assignors

LYSENKOV, ILYA

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC