US 11,948,271 B2
Machine learning techniques for video downsampling
Li-Heng Chen, Austin, TX (US); Christos G. Bampis, Los Gatos, CA (US); and Zhi Li, Mountain View, CA (US)
Assigned to NETFLIX, INC., Los Gatos, CA (US)
Filed by NETFLIX, INC., Los Gatos, CA (US)
Filed on Dec. 23, 2020, as Appl. No. 17/133,206.
Prior Publication US 2022/0198607 A1, Jun. 23, 2022
Int. Cl. G06T 3/40 (2006.01); G06N 3/084 (2023.01); G06T 3/4046 (2024.01); G06T 9/00 (2006.01)
CPC G06T 3/4046 (2013.01) [G06N 3/084 (2013.01); G06T 9/002 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A computer-implemented method for training a neural network to downsample images in a video encoding pipeline, the method comprising:
executing a first convolutional neural network on a first source image having a first resolution to generate a first downsampled image, wherein the first convolutional neural network includes at least two residual blocks;
executing an upsampling algorithm on the first downsampled image to generate a first reconstructed image having the first resolution;
computing a first reconstruction error based on the first reconstructed image and the first source image; and
updating at least one parameter of the first convolutional neural network based on the first reconstruction error to generate a trained convolutional neural network.