Residual neural network based on hole convolution and two-stage image demosaicing method

Abstract

The invention belongs to the field of digital image processing, and particularly relates to a residual neural network based on hole convolution and a two-stage image demosaicing method. According to the invention, a shallow feature extraction unit, a local residual unit and a deep feature extraction unit are introduced based on a residual neural network; the interaction of the three basic units greatly enhances the learning ability and modeling ability of the target neural network. Accurate mapping from the mosaic image to the RGB color image can be established for the image demosaicing problem, and finally the mosaic image in the Bayer CFA mode can be processed through the established effective mapping to obtain the RGB color image; meanwhile, a two-stage image demosaicing model is introduced, prior information is fully utilized, the modeling capability of the network is improved, and the understanding space is optimized; by means of the image demosaicing method, the peak signal-to-noise ratio of the image can be remarkably increased, the image demosaicing efficiency, quality and robustness are greatly improved, and the image demosaicing method has far-reaching significance in thefield of image processing.

Description

technical field [0001] The invention belongs to the field of digital image processing, in particular to a residual neural network based on hole convolution and a two-stage image demosaic method. Background technique [0002] Single-sensor color imaging technology using CFA is widely used in the current digital camera industry. In a single-sensor camera with CFA, each pixel only records one pixel in the R-channel image, G-channel image, and B-channel image. When restoring an RGB color image, it is necessary to estimate the values ​​of the other two lost pixels; This process is often called image demosaicing, and it plays a vital role in the field of obtaining high-quality RGB color images. The most popular and widely used CFA is BayerCFA. In the BayerCFA model, green pixels are sampled by a quincunx grid, and red and blue pixels are sampled by a rectangular grid, where the number of green sample points is the number of red or blue samples double the number of points. [00...

AI Technical Summary

Problems solved by technology

In the document "Color Image Demosaicking via Deep Residual Learning", CNN is used to implement image demosaicing, which has achieved a good performance gain compared with traditional methods, but due to the introduction of batch normalization (BN), under the premise of the same computing cost , which reduces the depth of the network, thereby reducing the network's perception domain

Images