WO2024176030 - SYSTEMS AND METHODS OF OPTIMIZED DEEP LEARNING FOR IMAGE RECONSTRUCTION
National phase entry is expected:
Publication Number
WO/2024/176030
Publication Date
29.08.2024
International Application No.
PCT/IB2024/051124
International Filing Date
07.02.2024
Title **
[English]
SYSTEMS AND METHODS OF OPTIMIZED DEEP LEARNING FOR IMAGE RECONSTRUCTION
[French]
SYSTÈMES ET PROCÉDÉS D'APPRENTISSAGE PROFOND OPTIMISÉ POUR RECONSTRUCTION D'IMAGE
Applicants **
CYENS COE
Inventors
JAMIL, Asfa
ARTUSI, Alessandro
Priority Data
18/172,640
22.02.2023
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
EPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 2194 | |
| EPO | Filing, Examination, Granting | 11154 | |
| Japan | Filing, Examination, Granting | 2400 | |
| South Korea | Filing, Examination, Granting | 2558 | |
| USA | Filing, Examination, Granting | 4740 |
Total:
23,046
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[English]
A deep learning network can have the following elements arranged in sequence: a convolutional block, a first residual block (RB), a first element-wise adder, a second RB, a second element-wise adder, and an upsampling unit. At least one processor can perform processing comprising generating a super resolution image by processing, with the deep learning network, an image having a resolution lower than a resolution of the super resolution image.[French]
L'invention concerne un réseau d'apprentissage profond qui peut avoir les éléments suivants, agencés en séquence : un bloc de convolution, un premier bloc résiduel (RB), un premier additionneur élément par élément, un deuxième RB, un deuxième additionneur élément par élément et une unité de suréchantillonnage. Au moins un processeur peut effectuer un traitement comprenant la génération d'une image à super-résolution par traitement, avec le réseau d'apprentissage profond, d'une image ayant une résolution inférieure à une résolution de l'image à super-résolution.