Video denoising method based on actual camera noise modeling

Abstract

The invention discloses a video denoising method based on actual camera noise modeling. The method comprises the following specific steps: (1) exploring the physical cause of main noise in an imaging process and establishing a mathematical model of noise distribution; (2) on the basis of the established noise model, carrying out model parameter calibration, and generating a noise video training set conforming to reality; (3) designing a video denoising and enhancement neural network, and combining space and time information to suppress and weaken the noise; and (4) training and optimizing the neural network, and verifying the practicability of the method by using the synthesized and actually acquired video data set. The de-noising method is suitable for de-noising weak light videos and has very important application requirements in the fields of national defense military affairs, security and protection monitoring, scientific research environment protection and the like.

Description

technical field [0001] The invention relates to the field of computational photography and deep learning, and in particular to the field of low-light video denoising based on actual camera noise modeling. Background technique [0002] Low-light video imaging is a challenging problem in extremely low-light conditions where large amounts of noise can significantly degrade image quality. A large number of video denoising or video enhancement algorithms have been proposed to solve this problem, however, most of the noise models in these algorithms are simple independent and identically distributed assumptions, including additive white Gaussian noise, Poisson noise or Gaussian noise and Poisson noise the mix of. In reality, noise in video is very complex, especially in low-light conditions, and some factors that are usually ignored, such as dynamic pattern noise, noise channel correlation, truncation effects, etc., will become major problems. [0003] Deep learning-based method...

AI Technical Summary

Problems solved by technology

[0002]In extremely low-light conditions, a large amount of noise can significantly degrade the image quality, so low-light video imaging is a challenging problem

A large number of video denoising or video enhancement algorithms have been proposed to solve this problem, however, most of the noise models in these algorithms are simple independent and identically distributed assumptions, including additive white Gaussian noise, Poisson noise or Gaussian noise and Poisson noise the mix of

In reality, noise in video is very complex, especially in low light conditions, and some factors that are usually ignored, such as dynamic pattern noise, noise channel connection, truncation effect, etc., will become major problems

Images