US 12,294,720 B2
Method and apparatus for dynamic learning rates of substitution in neural image compression
Sheng Lin, San Jose, CA (US); Ding Ding, Palo Alto, CA (US); Wei Jiang, Sunnyvale, CA (US); Wei Wang, Palo Alto, CA (US); Xiaozhong Xu, State College, PA (US); and Shan Liu, San Jose, CA (US)
Assigned to TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed by TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed on Oct. 13, 2021, as Appl. No. 17/500,355.
Claims priority of provisional application 63/176,206, filed on Apr. 16, 2021.
Prior Publication US 2022/0345717 A1, Oct. 27, 2022
Int. Cl. H04N 19/119 (2014.01); H04N 19/147 (2014.01); H04N 19/172 (2014.01); H04N 19/42 (2014.01); H04N 19/46 (2014.01)
CPC H04N 19/147 (2014.11) [H04N 19/119 (2014.11); H04N 19/172 (2014.11); H04N 19/42 (2014.11); H04N 19/46 (2014.11)] 18 Claims
OG exemplary drawing
 
1. A method of substitutional end-to-end (E2E) neural image compression (NIC) using a neural network performed by at least one processor, the method comprising:
receiving an input image to an E2E NIC framework;
mapping from the input image x0 in a high dimensional space to a bit-stream with length R(x0);
mapping the bit-stream with the length R(x0) to a compressed representation custom character;
determining whether there exists a substitution x′0 that is mapped to a substitution compressed representation custom character such that a first distance measurement or loss function between custom character and x0 is less than between a second distance measurement or loss function between custom character and x0;
when the substitution x′0 that is mapped to custom character that is closer to x0 given the second distance measurement or loss function exists, determining a substitute image based on a training model and a step size,
wherein, the substitute image is different from the input image;
encoding the substitute image to generate a compressed representation of the substitute image; and
outputting, as an encoding of the input image for decoding by a decoder, the compressed representation of the substitute image,
wherein the compressed representation of the substitute image replaces a compressed representation of the input image in the E2E NIC framework.