Image super-resolution method based on dense connection network

Abstract

The invention discloses an image super-resolution method based on dense connection network. By increasing the depth of a convolution neural network and introducing a large quantity of jumping connection in the deep network, the image super-resolution method based on dense connection network effectively solves the problem that the gradient disappears during the reverse propagation of the deep network, optimizes flowing of information on the network, and improves the super-resolution reconstruction capability of the convolution neural network. At the same time, the image super-resolution method based on dense connection network is effectively combined with the bottom layer characteristic and the high layer abstract characteristic, and can reduce the model parameters and compress the deep network model so as to improve the reconstruction efficiency of the image super-resolution. Besides, by introducing a deep monitoring technology, the image super-resolution method based on dense connection network can reconstruct the super-resolution image at different depth of network, thus not only optimizing training of the deep network, but also being able to selecting a suitable network depth to reconstruct a high definition image according to the calculation capability of the test terminal during the testing process. Finally, the image super-resolution method based on dense connection network utilizes an image ser having a plurality of amplification factors to train, so that the obtained model can perform image super-resolution on a plurality of dimensions and does not need to train different models for every amplification factor.

Description

technical field [0001] The invention relates to the field of computer vision and artificial intelligence technology, in particular to an image super-resolution method based on a densely connected network. Background technique [0002] In the field of computer vision, most of the problems have been solved using deep neural networks with wide success. In many computer vision tasks, such as face recognition, target detection and tracking, image retrieval, etc., the algorithm using the deep neural network model has greatly improved the performance of the traditional algorithm. In the task of image super-resolution reconstruction, the latest work has also begun to use the nonlinear feature representation ability of convolutional neural network to improve the reconstruction effect of image super-resolution. After searching the literature of the prior art, it was found that the patent name "A method for image super-resolution reconstruction" (Chinese Patent Publication No. CN10597...

AI Technical Summary

Problems solved by technology

However, the VDSR algorithm still simply stacks the convolutional layer and the activation layer together, which is not conducive to the flow of gradient information and brings difficulties to optimize deeper networks.

At the same time, this simple stacking method cannot effectively use the features trained by each layer, and the network model parameters are also very large.

For example, the 20-layer network of the VDSR algorithm requires more than 700,000 model parameters, which not only brings difficulties to optimization, but also increases the computational complexity of super-resolution reconstruction.

Images