US 11,057,634 B2
Content adaptive optimization for neural data compression
Christopher Schroers, Zürich (CH); Simon Meierhans, Zürich (CH); Joaquim Campos, St. Sulpice (CH); Jared McPhillen, Glendale, CA (US); Abdelaziz Djelouah, Zürich (CH); Erika Varis Doggett, Los Angeles, CA (US); Scott Labrozzi, Cary, NC (US); and Yuanyi Xue, Kensington, CA (US)
Assigned to Disney Enterprises, Inc., Burbank, CA (US)
Filed by Disney Enterprises, Inc., Burbank, CA (US)
Filed on May 15, 2019, as Appl. No. 16/413,414.
Prior Publication US 2020/0366914 A1, Nov. 19, 2020
Int. Cl. H04N 19/42 (2014.01); G06N 3/02 (2006.01); H04N 19/186 (2014.01); H04N 19/513 (2014.01); G06N 7/00 (2006.01)
CPC H04N 19/42 (2014.11) [G06N 3/02 (2013.01); G06N 7/005 (2013.01); H04N 19/186 (2014.11); H04N 19/513 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A data processing system comprising:
a computing platform including a hardware processor and a system memory storing a data compression software code, a trained neural encoder and a trained neural decoder, wherein the trained neural encoder and the trained neural decoder each includes parameters of a latent space probability model determined during training using a neural network;
the hardware processor configured to execute the data compression software code to:
receive a plurality of compression input data;
encode, using the trained neural encoder, a first compression input data of the plurality of compression input data to a latent space representation of the first compression input data;
decode, using the trained neural decoder, the latent space representation of the first compression input data to produce an input space representation of the first compression input data corresponding to the latent space representation of the first compression input data;
generate, using additive noise, first compression input data refined latent values based on a comparison of the first compression input data with the input space representation;
re-encode, using the trained neural encoder, the first compression input data using the first compression input data refined latent values to produce a first compressed data corresponding to the first compression input data; and
transmit the first compressed data to a remote trained neural decoder having the parameters of the latent space probability model;
wherein encoding, decoding and generating the first compression input data refined latent values do not change any of the parameters of the latent space probability model of each of the trained neural encoder and the trained neural decoder, thereby not requiring any change to any parameter of the latent space probability model of the remote trained neural decoder.