Title:
SPECTRAL CROSS-DOMAIN TRANSFER SUPER-RESOLUTION RECONSTRUCTION METHOD FOR MULTI-DOMAIN IMAGE
Document Type and Number:
WIPO Patent Application WO/2024/082796
Kind Code:
A1
Abstract:
A spectral cross-domain transfer super-resolution reconstruction method for a multi-domain image. By means of a spectral image cross-domain transfer super-resolution reconstruction method, which is based on cross-domain transferable knowledge learning and rapid target-domain adaptation learning, for a multi-domain image scenario, spectral super-resolution reconstruction from an RGB image to a hyperspectral image is realized. A model structure design based on a transferable dictionary is used to learn cross-domain transferable features; a source-domain pre-training policy based on a shared learnable mask is used to facilitate a model in learning general knowledge for reconstruction; and a model-agnostic meta-learning fine-tuning method is used to learn a universal model with a strong generalization capability, such that the model can adapt to data of a target domain of a test by means of several iterations of test data. The method can mine cross-domain shared knowledge to improve the generalization capability, thereby improving the effect of spectral cross-domain super-resolution reconstruction.
Inventors:
ZHANG YANNING (CN)
ZHANG LEI (CN)
WEI WEI (CN)
REN WEIXIN (CN)
WANG HAOYU (CN)
ZHANG LEI (CN)
WEI WEI (CN)
REN WEIXIN (CN)
WANG HAOYU (CN)
Application Number:
PCT/CN2023/113283
Publication Date:
April 25, 2024
Filing Date:
August 16, 2023
Export Citation:
Assignee:
UNIV NORTHWESTERN POLYTECHNICAL (CN)
International Classes:
G06T3/40
Foreign References:
| US20220366536A1 | 2022-11-17 | |||
| CN110232653A | 2019-09-13 | |||
| CN111932461A | 2020-11-13 | |||
| CN114332649A | 2022-04-12 | |||
| CN111369433A | 2020-07-03 |
Attorney, Agent or Firm:
ZHENGZHOU YUYUAN INTELLECTUAL PROPERTY AGENCY OFFICE (GENERAL PARTNERSHIP) (CN)
Download PDF: