Title:
LEARNED IMAGE COMPRESSION BASED ON FAST RESIDUAL CHANNEL ATTENTION NETWORK
Document Type and Number:
WIPO Patent Application WO/2024/077738
Kind Code:
A1
Abstract:
According to one aspect of the present disclosure, a method of video post-processing may include receiving, by a processor, a plurality of input feature maps associated with an image. The plurality of input feature maps may be generated by a video pre-processing network. The video post-processing method may include inputting, by the processor, the plurality of input feature maps into a first depth-wise separable convolutional (DSC) network of a fast residual channel attention network (FRCAN) component. The video post-processing method may include outputting, by the processor, a first set of output feature maps from the first DSC network of the FRCAN component.
Inventors:
JUNG CHEOLKON (CN)
HU YUSONG (CN)
HU YUSONG (CN)
Application Number:
PCT/CN2022/135890
Publication Date:
April 18, 2024
Filing Date:
December 01, 2022
Export Citation:
Assignee:
GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD (CN)
International Classes:
G06T7/00
Foreign References:
| CN113313644A | 2021-08-27 | |||
| CN114037071A | 2022-02-11 | |||
| CN113792641A | 2021-12-14 | |||
| CN114283151A | 2022-04-05 |
Attorney, Agent or Firm:
SCIHEAD IP LAW FIRM (CN)
Download PDF: