A Novel Technique for Converting Images from 2D to 3D using Deep Neural Networks

The conversion of 2D images into 3D images has been a crucial scientific problem. In the industries of computer graphics and animations, medical imaging augmented and virtual reality, and others, reconstruction of 3D images from 2D images is high in demand. Researchers deploy convolutional networks for the reconstruction of 3D images. This paper compares the existing techniques and proposes a MeshCNN-based nove1 technique to convert 2D images into 3D images. The publicly available dataset namely VisDrone is used for experimental study. The proposed technique has been validated against the existing techniques. It is concluded that the proposed model has the potential to effectively convert 2D images into 3D images.