3D-Slice-Super-Resolution-Net: A Fast Few Shooting Learning Model for 3D Super-resolution Using Slice-up and Slice-reconstruction

Abstract

A 3D model is a storage method that can accurately describe the objective world. However, the establishment of a 3D model requires a lot of acquisition resources in details, and a precise 3D model often consumes abundant storage space. To eliminate these drawback, we propose a 3D data super-resolution model named three dimension slice reconstruction model(3DSR) that use low resolution 3D data as input to acquire a high resolution result instantaneously and accurately, shortening time and storage when building a precise 3D model. To boost the efficiency and accuracy of deep learning model, the 3D data is split as multiple slices. The 3DSR processes the slice to high resolution 2D image, and reconstruct the image as high resolution 3D data. 3D data slice-up method and slice-reconstruction method are designed to maintain the main features of 3D data. Meanwhile, a pre-trained deep 2D convolution neural network is utilized to expand the resolution of 2D image, which achieve superior performance. Our method saving the time to train deep learning model and computation time when improve the resolution. Furthermore, our model can achieve better performance even less data is utilized to train the model.