Patent · US Active

3D hair synthesis using volumetric variational autoencoders

US11074751B2 · kind B2 · utility

0Cited by

2References

17Claims

0Family size

Assignee

University of Southern California · US

Inventors

Hao Li · New York, US
Liwen Hu · Los Angeles, US
Shunsuke Saito · Los Angeles, US

Key dates

Filing date	Dec 4, 2019
Grant date	Jul 27, 2021
Priority date	—
Expiry date	Dec 4, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06T2219/2004
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Devices and methods for single-view 3D hair modeling are disclosed. The method for single-view 3D hair modeling includes training, by a neural network processor, a volumetric autoencoder to encode a plurality of 3D hairstyles into latent features, and to generate an output based on the latent features. The method for single-view 3D hair modeling includes training, by the neural network processor, an embedding network to determine hair coefficients of a single hairstyle from an input image. The method for single-view 3D hair modeling includes receiving, by the neural network processor, the input image. The method for single-view 3D hair modeling includes synthesizing, by the neural network processor, hair strands to generate a single-view 3D model of the single hairstyle based on the volumetric autoencoder, the embedding network, and the input image.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.