Image Super-Resolution Reconstruction Based on Disparity Map and CNN

Abstract

This paper presents a new method for registration of digital micro-mirror device (DMD) cameras through image reconstruction. The method called dual-channel super-resolution reconstruction (DCSR) uses a dual-channel input convolutional neural network method to iteratively obtain high resolution images. The originality of this study relies on the input color weight disparity map that enables extracting edges cues and feature cues effectively during the super-resolution. The iterative initial disparity map is obtained by a cost aggregation method based on the color weights, and the model parameters are updated during the iterative process. To validate performance, a series of the comparison experiments is developed on different network structures and parameter settings for the diverse deconv-pooling layers, convolution kernel sizes, and activation function. Experimental results show that the DCSR method can solve the sub-pixel registration problem of DMD cameras and achieve a good image reconstruction effect. The DCSR performs higher accuracy and an efficient process compared with traditional reconstruction made by single-channel input convolution neural network. The spatial resolution of the reconstructed image is significantly improved, and the detail resolution is enhanced.