Shape From Shading Problem Using Deep Learning

Abstract

Given a single 2D image, our Objective is to pass that image into a Deep Learning Model and get the 3D shape of that image as output. These tasks have received many attentions recently, however, most of this existing approaches rely on 3D supervision, annotation of 2D images with keypoints , and also training with multiple views of each object instance, also known as Photometric stereo method. My frameworks are all based on the GAN architecture, with some custom made data set and also data from the ShapeNet data set, the models can run only on 2D images. Our model takes in a single image, encodes it into a latent code Z and passes it onto a generator, which the subsequently produces the depth image, which is used to construct the point cloud . The use of point cloud in the output representation, makes it possible for us to exploit the depth image of the object from the training image.