An adaptive image super-resolution system
A super-resolution and adaptive technology, applied in the field of image restoration, can solve the problem that the image super-resolution system cannot be adaptively adjusted, and achieve the effect of reducing the amount of calculation and improving the calculation efficiency.
Active Publication Date: 2021-05-07
HARBIN INST OF TECH
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention proposes an adaptive image super-resolution system in order to solve the problem that the existing image super-resolution system cannot be adaptively adjusted according to application scenarios and needs
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0046] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.
[0047] see figure 1 Describe this embodiment, an adaptive image super-resolution system described in this embodiment includes a depth super-resolution backbone network, and also includes a network depth prediction module; wherein, the depth super-resolution backbone network includes a feature ext...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
An adaptive image super-resolution system belongs to the field of image restoration. The invention aims to solve the problem that the existing image super-resolution system cannot perform self-adaptive adjustment according to application scenarios and needs. The invention includes a network depth prediction module, a feature extraction module, a processing module, an adder, an upsampling module and an image restoration module; the feature extraction module is used to perform feature extraction on the original low-resolution image to obtain a feature extraction map; network depth prediction module, according to the preset expected value of network depth d * Carry out adaptive convolution operation on all the feature points in the feature extraction map to predict the network depth map; the processing module is used to process the feature extraction map according to the received network depth map to obtain the residual of all the feature points in the feature extraction map difference feature; an adder, which is used to superimpose the residual features of all feature points on the corresponding feature points in the feature extraction map, thereby adjusting the feature extraction map to obtain the adjusted feature extraction map, and through the up-sampling module. The image is extracted and enlarged, and then repaired by the image restoration module to complete the restoration of the image. The present invention is mainly used for restoring low-resolution images.
Description
technical field [0001] The invention relates to a single image super-resolution system, which belongs to the field of image restoration. Background technique [0002] Image super-resolution aims to restore high-resolution images from low-resolution images. The main reasons for the appearance of low-resolution images are limitations of hardware conditions, down-sampling during transmission and storage, etc. In applications such as medical images, monitoring, and entertainment, images with higher resolution are often required. Therefore, image super-resolution has always been a research hotspot. [0003] In recent years, with the development of convolutional neural network and deep learning technology, the performance of super-resolution models is often closely related to the depth of the network. However, there are differences in the processing difficulty of different regions in the super-resolution task, and mainstream methods perform the same processing on different regi...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/40G06N3/04G06N3/08
CPCG06T3/4076G06N3/08G06N3/045
Inventor 左旺孟刘铭张志路
Owner HARBIN INST OF TECH