Title:
RECEIVER FOR DATA DECOMPRESSION WITH AUTO-ENCODER ENHANCEMENT
Document Type and Number:
WIPO Patent Application WO/2024/079339
Kind Code:
A1
Abstract:
The invention relates to a receiver (120) comprising: - a memory (502) storing a first auto-encoder convolutional neural network designed to obtain enhanced data from compressed data; - a first interface (503) designed to receive compressed data over a communication channel (130); - a processor (501) configured to decompress the data into decompressed data, and to apply the first auto-encoder convolutional neural network to the compressed data to obtain enhanced data; and - a second interface (504) designed to transmit the enhanced data.
More Like This:
Inventors:
ALMEHIO YASSER (FR)
Application Number:
PCT/EP2023/078545
Publication Date:
April 18, 2024
Filing Date:
October 13, 2023
Export Citation:
Assignee:
VALEO VISION (FR)
International Classes:
G06N3/0455; B60Q1/14; G06N3/0464; G06N3/063; G06N3/08; G06N3/088; G06N3/09; H04N19/85; H05B47/18
Domestic Patent References:
| WO2022090372A1 | 2022-05-05 |
Other References:
AHONEN JUKKA I ET AL: "Learned Enhancement Filters for Image Coding for Machines", 2021 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), IEEE, 29 November 2021 (2021-11-29), pages 235 - 239, XP034000019, DOI: 10.1109/ISM52913.2021.00046
NAM LE ET AL: "Image coding for machines: an end-to-end learned approach", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 23 August 2021 (2021-08-23), XP091036146, DOI: 10.1109/ICASSP39728.2021.9414465
DONG CHAO ET AL: "Compression Artifacts Reduction by a Deep Convolutional Network", 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), IEEE, 7 December 2015 (2015-12-07), pages 576 - 584, XP032866378, DOI: 10.1109/ICCV.2015.73
MA DI ET AL: "MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering", IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, IEEE, US, vol. 15, no. 2, 9 December 2020 (2020-12-09), pages 378 - 387, XP011840005, ISSN: 1932-4553, [retrieved on 20210219], DOI: 10.1109/JSTSP.2020.3043064
NAM LE ET AL: "Image coding for machines: an end-to-end learned approach", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 23 August 2021 (2021-08-23), XP091036146, DOI: 10.1109/ICASSP39728.2021.9414465
DONG CHAO ET AL: "Compression Artifacts Reduction by a Deep Convolutional Network", 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), IEEE, 7 December 2015 (2015-12-07), pages 576 - 584, XP032866378, DOI: 10.1109/ICCV.2015.73
MA DI ET AL: "MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering", IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, IEEE, US, vol. 15, no. 2, 9 December 2020 (2020-12-09), pages 378 - 387, XP011840005, ISSN: 1932-4553, [retrieved on 20210219], DOI: 10.1109/JSTSP.2020.3043064
Attorney, Agent or Firm:
LOTAUT, Jonathan (FR)
Download PDF: