Title:
SYSTEMS AND METHODS FOR AUTOENCODING RESIDUAL DATA IN CODING OF A MULTI-DIMENSIONAL DATA
Document Type and Number:
WIPO Patent Application WO/2022/209828
Kind Code:
A1
Abstract:
A method of encoding data is disclosed. The method comprising: receiving a residual data set having a size specified by a number of channels dimension, a height dimension, and a width dimension; generating an intermediate data set corresponding to the residual data set; adding the intermediate data set to the residual data to generate a modified residual dataset; generating an output data set corresponding to the received residual data set by performing a discrete convolution on the modified residual data set, wherein performing a discrete convolution includes spatial down-sampling the modified residual data set according to a number of instances of kernels; and signaling the generated output data set in a bitstream.
Inventors:
MISRA KIRAN MUKESH
JI TIANYING
SEGALL CHRISTOPHER ANDREW
JI TIANYING
SEGALL CHRISTOPHER ANDREW
Application Number:
PCT/JP2022/011396
Publication Date:
October 06, 2022
Filing Date:
March 14, 2022
Export Citation:
Assignee:
SHARP KK (JP)
International Classes:
H04N19/59; H04N19/90
Foreign References:
| US20190158884A1 | 2019-05-23 | |||
| US20210044804A1 | 2021-02-11 |
Other References:
LU GUO; ZHANG XIAOYUN; OUYANG WANLI; CHEN LI; GAO ZHIYONG; XU DONG: "An End-to-End Learning Framework for Video Compression", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, IEEE COMPUTER SOCIETY., USA, vol. 43, no. 10, 20 April 2020 (2020-04-20), USA , pages 3292 - 3308, XP011875084, ISSN: 0162-8828, DOI: 10.1109/TPAMI.2020.2988453
MAN M. HO; JINJIA ZHOU; GANG HE: "RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 25 February 2020 (2020-02-25), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081860434, DOI: 10.1109/TIP.2020.3046872
LEE SOONBIN: "Learned Image Compression with Frequency Domain Loss", 2021 INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN), IEEE, 2 February 2021 (2021-02-02), XP055973752, DOI: 10.1109/ICOIN50884.2021.9333956
MAN M. HO; JINJIA ZHOU; GANG HE: "RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 25 February 2020 (2020-02-25), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081860434, DOI: 10.1109/TIP.2020.3046872
LEE SOONBIN: "Learned Image Compression with Frequency Domain Loss", 2021 INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN), IEEE, 2 February 2021 (2021-02-02), XP055973752, DOI: 10.1109/ICOIN50884.2021.9333956
Attorney, Agent or Firm:
INOUE Tomoya (JP)
Download PDF:
Previous Patent: FOAM RUBBER LATEX COMPOSITION AND FOAM RUBBER
Next Patent: OPTICAL MULTILAYER BODY AND IMAGE DISPLAY DEVICE
Next Patent: OPTICAL MULTILAYER BODY AND IMAGE DISPLAY DEVICE