Reviews: Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision

This paper attempts to reconstruct a 3D volume for an object from a single image at test time. During training time it uses a number of views of the object to reconstruct a 3D volume containing the object where the volume is broken down into smaller voxels and the network predicts whether each voxel is occupied or not. The input is an image of the object only against a white background. They chose to ignore color and texture in their reconstruction work. The network they suggest is an encoder-decoder network where one half encodes an images into a 3D invariant latent representation and the decoder does dense reconstruction of only that object.