Real image denoising method based on multi-scale selection feedback network

A feedback network and real image technology, applied in the field of computer vision and image processing, can solve the problems of reducing excessive dependence on clean and high-quality training data, high complexity of denoising models, and robustness of noise changes, achieving superior denoising performance, The effect of low model complexity and reduced dependence on training data
CN112927159BActive Publication Date: 2022-08-02SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
10 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
Publication Date
2022-08-02

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a real image denoising method based on a multi-scale selection feedback network, comprising: constructing a multi-scale selection module MSB for extracting multiple receptive field scale features; constructing a multi-scale selection feedback network MSFB, including a shallow feature extraction unit , multiple concatenated MSBs, image reconstruction units, and degradation models; construct two dual tasks for image denoising: predict noise-free images from original noisy images, and degrade from predicted noise-free images to noisy images; exploit MSFB at multiple times Two dual tasks are repeatedly performed in the step, and multi-level iteration is performed; in the iteration, the high-level semantic information output by the deep MSB of the previous time step is selectively fed back to the input of the shallow MSB of the next time step, and the MSFB is trained iteratively; In the training process, the optimization goal is to minimize the dual loss, and the peak signal-to-noise ratio is used as the evaluation index of the network performance; the noisy image is input into the trained MSFB for denoising, and the denoised image is output.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the fields of computer vision and image processing, in particular to a real image denoising method based on a multi-scale selection feedback network. Background technique

[0002] When the real image is processed, stored, and transmitted in the acquisition system, a variety of complex noises will be generated, resulting in the loss of structural details and the degradation of image quality. And image noise will also be subject to such decomposition and synthesis. The electrical system and external influences in these processes complicate the precise analysis of image noise. Most of the denoising methods that exist today are based on known synthetic additive white Gaussian noise, but tend to perform poorly in real-world noisy images.

[0003] Image denoising is a typical image restoration task. The characteristic of direct image-to-image conversion results in an infinite number of correspondences for noisy images in the clean ...

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