A single image enhancement method based on full convolution neural network
A convolutional neural network, single-image technology, applied in the field of single-image enhancement based on full convolutional neural network, can solve the problem of unable to recover the details of the low dark area of the image and so on
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0045] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0046] Due to the limitation of the dynamic range of the camera sensor, there is a phenomenon of information loss in the single-exposure image. For this, the present invention proposes a single-image enhancement method based on a fully convolutional neural network. Therefore, the single-exposure image is used to generate a low / high-exposure image different from its exposure to restore the lost information; and then the neural network is used to extract the fusion features of the multi-exposure sequence to reconstruct the final enhanced image.
[0047] The overall realization flow chart of the inventive method is as figure 1 Shown, the inventive method comprises the following steps:
[0048] Step 1: Construct two cascaded networks, the first network is the prediction exposure network, and the second network is the exposure fusion network;
[...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com