US 11,727,628 B2
Neural opacity point cloud
Cen Wang, Shanghai (CN); and Jingyi Yu, Shanghai (CN)
Assigned to ShanghaiTech University, Shanghai (CN)
Filed by SHANGHAITECH UNIVERSITY, Shanghai (CN)
Filed on Nov. 4, 2022, as Appl. No. 17/980,754.
Application 17/980,754 is a continuation of application No. PCT/CN2020/089959, filed on May 13, 2020.
Prior Publication US 2023/0071559 A1, Mar. 9, 2023
Int. Cl. G06T 15/20 (2011.01); G06T 7/80 (2017.01); G06T 7/55 (2017.01); G06T 7/194 (2017.01); G06T 15/50 (2011.01)
CPC G06T 15/205 (2013.01) [G06T 7/194 (2017.01); G06T 7/55 (2017.01); G06T 7/80 (2017.01); G06T 15/20 (2013.01); G06T 15/503 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2210/52 (2013.01); G06T 2210/56 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A method of rendering an object, the method comprising:
encoding a feature vector to each point in a point cloud for an object, wherein the feature vector comprises an alpha matte;
projecting each point in the point cloud and the corresponding feature vector to a target view to compute a feature map; and
using a neural rendering network to decode the feature map into a RGB image and the alpha matte and to update the feature vector.