Liwen Hu

US Patent:

20200175757, Jun 4, 2020

Filed:

Dec 4, 2019

Appl. No.:

16/703582

Inventors:

- Los Angeles CA, US
Liwen Hu - Los Angeles CA, US
Shunsuke Saito - Los Angeles CA, US

International Classification:

G06T 17/20
G06T 19/20
G06T 7/10

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.

US Patent:

20180374242, Dec 27, 2018

Filed:

Aug 31, 2018

Appl. No.:

16/119907

Inventors:

- Westlake Village CA, US
Liwen Hu - Los Angeles CA, US
Lingyu Wei - Los Angeles CA, US
Koki Nagano - Los Angeles CA, US
Jaewoo Seo - Los Angeles CA, US
Jens Fursund - Copenhagen, DK

International Classification:

G06T 11/00
G06T 15/00
G06T 17/20
G06K 9/00
G06T 7/11
G06N 3/08
G06N 5/04

Abstract:

A system for generating three-dimensional facial models including photorealistic hair and facial textures includes creating a facial model with reliance upon neural networks based upon a single two-dimensional input image. The photorealistic hair is created by finding a subset of similar three-dimensional polystrip hairstyles from a large database of polystrip hairstyles, selecting the most-alike polystrip hairstyle, deforming that polystrip hairstyle to better fit the hair of the two-dimensional image. Then, collisions and bald spots are corrected, and suitable textures are applied. Finally, the facial model and polystrip hairstyle are combined into a final three-dimensional avatar.

US Patent:

20180181802, Jun 28, 2018

Filed:

Dec 28, 2016

Appl. No.:

15/392597

Inventors:

- San Jose CA, US
DUYGU CEYLAN - Mountain View CA, US
BYUNGMOON KIM - Sunnyvale CA, US
LIWEN HU - Los Angeles CA, US
JIMEI YANG - Santa Clara CA, US

International Classification:

G06K 9/00
G06T 7/73

Abstract:

Certain embodiments involve recognizing combinations of body shape, pose, and clothing in three-dimensional input images. For example, synthetic training images are generated based on user inputs. These synthetic training images depict different training figures with respective combinations of a body pose, a body shape, and a clothing item. A machine learning algorithm is trained to recognize the pose-shape-clothing combinations in the synthetic training images and to generate feature descriptors describing the pose-shape-clothing combinations. The trained machine learning algorithm is outputted for use by an image manipulation application. In one example, an image manipulation application uses a feature descriptor, which is generated by the machine learning algorithm, to match an input figure in an input image to an example image based on a correspondence between a pose-shape-clothing combination of the input figure and a pose-shape-clothing combination of an example figure in the example image.

US Patent:

20180158240, Jun 7, 2018

Filed:

Dec 1, 2017

Appl. No.:

15/829064

Inventors:

- Westlake Village CA, US
Cosimo Wei - Los Angeles CA, US
Liwen Hu - Los Angeles CA, US
Hao Li - Santa Monica CA, US

International Classification:

G06T 17/20
G06K 9/00
G06K 9/66

Abstract:

A method for generating three-dimensional facial models and photorealistic textures from inferences using deep neural networks relies upon generating a low frequency and a high frequency albedo map of the full and partial face, respectively. Then, the high frequency albedo map may be used for comparison with correlation matrices generated by a neural network trained by a large scale, high-resolution facial dataset with simulated partial visibility. The corresponding correlation matrices of the complete facial textures can then be retrieved. Finally, a full facial texture map may be synthesized, using convex combinations of the correlation matrices. A photorealistic facial texture for the three-dimensional face rendering can be obtained through optimization using the deep neural network and a loss function that incorporates the blended target correlation matrices.