US 11,783,511 B2
Channel-wise autoregressive entropy models for image compression
David Charles Minnen, Mountain View, CA (US); and Saurabh Singh, Mountain View, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Dec. 23, 2022, as Appl. No. 18/88,283.
Application 18/088,283 is a continuation of application No. 17/021,688, filed on Sep. 15, 2020, granted, now 11,538,197, issued on Dec. 27, 2022.
Prior Publication US 2023/0206512 A1, Jun. 29, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 9/00 (2006.01); G06F 17/18 (2006.01); G06N 3/08 (2023.01); G06N 3/045 (2023.01)
CPC G06T 9/002 (2013.01) [G06F 17/18 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
for each slice in an ordinal sequence of slices, wherein each slice is a quantized latent representation of data that is different from each other slice of quantized latent representation of data, and the slices are arranged in an ordinal sequence:
receiving, by a first slice processing network, hyperprior parameters representing a probability distribution of an entropy model and a first slice of quantized latent representation of data, and generating, by the first slice processing network, a compressed representation of the first slice, and a first augmented slice that represents the first slice of quantized latent representation of data and a latent residual prediction that is a prediction of a residual encoding and decoding error based on the hyperprior parameters;
for each slice subsequent to the first slice in the ordinal sequence of slices:
receiving, by a respective subsequent slice processing network, the hyperprior parameters representing the probability distribution of the entropy model and each respective augmented slice generated by each prior respective subsequent slice processing network and the first slice processing network, and generating, by the respective subsequent slice processing network, a compressed representation of the respective slice, a respective subsequent augmented slice that represents the respective subsequent slice of quantized latent representation of data and a respective latent residual prediction that is a prediction of a residual encoding and decoding error based on the hyperprior parameters and each prior subsequent augmented slice;
wherein a combination of the compressed representation of the first slice and each compressed representation of each respective slice form a compressed representation of data processed using a first encoder neural network to generate a latent representation of the data.