A near-infrared image-guided cross-modal stereo image super-resolution reconstruction method
By constructing an image super-resolution reconstruction convolutional neural network in a multi-camera cross-spectral imaging system, combining cross-view angle matching and cross-modal feature migration modules, the problem of difficulty in recovering image texture information is solved, and the effective reconstruction of high-resolution visible light images is achieved.
CN114782248BActive Publication Date: 2025-03-18FUDAN UNIVERSITY
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202210380855.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-10
- Publication Date
- 2025-03-18
- Estimated Expiration
- 2042-04-10
AI Technical Summary
Technical Problem
In multicamera cross-spectral imaging systems, it is difficult to directly use near-infrared images acquired from different viewing angles to guide the super-resolution reconstruction of visible images, making it difficult to effectively restore image texture information.
Method used
By constructing an image super-resolution reconstruction convolutional neural network, combining cross-view angle matching and cross-modal feature migration modules, the information alignment and fusion of near-infrared images can be used to generate high-resolution visible light images.
Benefits of technology
It effectively improves the resolution of visible light mode images, enhances the subjective visual effects and objective accuracy of the image, and restores richer image texture details.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention belongs to the field of image editing technology, and specifically is a cross-modal stereo image super-resolution reconstruction method guided by near-infrared images. The present invention includes: using a cross-view matching module to extract the disparity between the left and right images of different modes of a stereo image, and then aligning the near-infrared image of the right view to the left view according to the disparity; the image super-resolution reconstruction network uses two network branches to extract the features of the left and right images of the stereo image respectively; using a cross-modal feature migration module to fuse the features of the left and right images; when reconstructing the image of the visible light modality of the left view of the stereo image, the image spatial information of the visible light modality is used, combined with the rich details contained in the near-infrared image of the corresponding right view to assist the super-resolution process of the left image, thereby generating more high-frequency detail textures in the image and restoring a more realistic high-resolution image. Experimental results show that the present invention can effectively improve the resolution of visible light modality images, enhance the subjective visual effect of the image, and the objective accuracy.
Need to check novelty before this filing date? Find Prior Art