An image super-resolution method based on omnidirectional spatial feature learning, a terminal and a storage medium

By employing an omnidirectional spatial feature learning method, image features are comprehensively captured and high-frequency textures are restored, solving the problem of incomplete feature extraction in existing technologies and achieving high-quality image super-resolution reconstruction.

CN122415337APending Publication Date: 2026-07-17SHENZHEN MSU-BIT UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHENZHEN MSU-BIT UNIVERSITY
Filing Date
2026-03-31
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing image super-resolution methods suffer from incomplete feature extraction, easy loss of high-frequency textures, and limited feature aggregation methods, resulting in poor reconstructed image quality.

Method used

An omnidirectional spatial feature learning-based approach is adopted. An initial shallow feature map is extracted through an encoder network. Multiple cascaded omnidirectional feature extraction modules are combined to extract spatial, channel and multi-scale detail-aware features. A high-frequency texture enhancement module is used to restore texture information and context-aware feature aggregation is performed. Finally, implicit decoding is performed to reconstruct a high-resolution image.

Benefits of technology

It achieves comprehensive capture of image features, effectively restores high-frequency textures, and performs intelligent feature aggregation, thereby improving the quality and detail fidelity of image reconstruction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122415337A_ABST
    Figure CN122415337A_ABST
Patent Text Reader

Abstract

The application discloses an image super-resolution method based on omnidirectional space feature learning, a terminal and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: using an encoder network to extract an initial shallow feature map of an input low-resolution image; inputting the initial shallow feature map into a deep feature extraction network composed of a plurality of cascaded omnidirectional feature extraction modules to perform spatial relationship perception feature extraction, channel relationship perception feature extraction and multi-scale detail perception feature extraction on the initial shallow feature map, and obtaining an omnidirectional feature map; inputting the omnidirectional feature map into a high-frequency texture enhancement module to perform frequency modulation feature enhancement and sparse non-local feature extraction on the omnidirectional feature map, and generating a texture enhancement feature map; performing context-aware feature aggregation on the texture enhancement feature map to obtain an aggregated feature vector; and performing implicit decoding and image reconstruction on the aggregated feature vector to obtain a high-resolution image. The application can comprehensively capture image features, effectively restore high-frequency textures and intelligently aggregate features.
Need to check novelty before this filing date? Find Prior Art