US 12,444,128 B2
Hair rendering system based on deep neural network
Haimin Luo, Shanghai (CN); Minye Wu, Shanghai (CN); Lan Xu, Shanghai (CN); and Jingyi Yu, Shanghai (CN)
Assigned to SHANGHAITECH UNIVERSITY, Shanghai (CN)
Appl. No. 18/281,966
Filed by SHANGHAITECH UNIVERSITY, Shanghai (CN)
PCT Filed Apr. 13, 2021, PCT No. PCT/CN2021/087069
§ 371(c)(1), (2) Date Sep. 14, 2023,
PCT Pub. No. WO2022/217470, PCT Pub. Date Oct. 20, 2022.
Prior Publication US 2024/0161388 A1, May 16, 2024
Int. Cl. G06T 15/20 (2011.01); G06T 7/593 (2017.01); G06T 7/62 (2017.01); G06T 17/00 (2006.01)
CPC G06T 15/20 (2013.01) [G06T 7/596 (2017.01); G06T 7/62 (2017.01); G06T 17/00 (2013.01); G06T 2200/04 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A method of rendering an object, comprising:
capturing a plurality of images of the object from a plurality of views;
obtaining an alpha mask for each of the plurality of images;
obtaining a 3D proxy geometry through a structure from a silhouette algorithm;
rendering a depth map for each of the plurality of images using a 3D proxy;
training a neural radiance field-based (NeRF-based) deep neural network with images with depth; and
rendering a plurality of images for a plurality of new views.