Image processing method and device based on full convolutional network, and computer equipment

Abstract

The invention relates to an image processing method and device based on a full convolutional network, and computer equipment. The image processing method comprises the steps: reducing the resolution of a first input image, obtaining a first low-resolution input image, inputting the first low-resolution input image into the full convolutional network, and obtaining a low-resolution output image; respectively converting the first input image and the first low-resolution input image into a second input image and a second low-resolution input image; utilizing an up-sampling method to obtain a processed image from the second low-resolution input image and the low-resolution output image, and calculating to obtain a first linear relation between the processed image and the second low-resolutioninput image; and obtaining a second linear relation between the second input image and the output image according to the first linear relation, and obtaining the output image according to the second linear relation and the second input image. The image processing method can be seamlessly connected with an existing trained network framework, has universality, and has an extremely high accelerationratio while not influencing the image processing quality.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image processing method, device and computer equipment based on a fully convolutional network. Background technique [0002] Deep learning technology has promoted the development of many image processing, such as image recognition, target detection, etc. Image processing based on deep learning technology such as image super-resolution reconstruction, dehazing, HDR, and detail enhancement has achieved particularly gratifying results, but deep learning Technology needs to process more data and deeper network, which leads to slower processing speed; due to the slow processing speed of deep learning, its application has great limitations. For example, image processing on mobile phones mostly uses traditional image processing technology , and its effect is significantly inferior to image processing based on deep learning techniques. [0003] Therefore, the prior...

AI Technical Summary

Problems solved by technology

[0002] Deep learning technology has promoted the development of many image processing, such as image recognition, target detection, etc. Image processing based on deep learning technology such as image super-resolution reconstruction, dehazing, HDR, and detail enhancement has achieved particularly gratifying results, but deep learning Technology needs to process more data and deeper network, which leads to slower processing speed; due to the slow processing speed of deep learning, its application has great limitations. For example, image processing on mobile phones mostly uses traditional image processing technology , its effect is obviously inferior to that of image processing based on deep learning technology

Images