Jin Yong Park

US Patent:

20220312017, Sep 29, 2022

Filed:

Jun 14, 2022

Appl. No.:

17/840126

Inventors:

- Austin TX, US
Sungsoo Kim - Austin TX, US
Jin Soo Park - Austin TX, US
Georgios Alex Dimakis - Austin TX, US

International Classification:

H04N 19/14
H04N 19/119
H04N 19/172
H04N 19/30
G06N 3/08
H04N 19/42
H04N 19/85
G06N 3/04
H04N 19/124

Abstract:

A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.

US Patent:

20210160509, May 27, 2021

Filed:

Nov 24, 2020

Appl. No.:

17/102743

Inventors:

- Austin TX, US
Sungsoo Kim - Austin TX, US
Jin Soo Park - Austin TX, US
Georgios Alex Dimakis - Austin TX, US

International Classification:

H04N 19/14
H04N 19/119
H04N 19/172
H04N 19/30
H04N 19/124
H04N 19/42
H04N 19/85
G06N 3/04
G06N 3/08

Abstract:

A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.