Scene Representation Networks: Continuous
  3D-Structure-Aware Neural Scene Representations

         Vincent Sitzmann Michael Zollhfer  Gordon Wetzstein
    {sitzmann, zollhoefer}@cs.stanford.edu, gordon.wetzstein@stanford.edu
                  Stanford University
                    vsitzmann.github.io/srns/

                           Abstract
       Unsupervised learning with generative models has the potential of discovering rich
       representations of 3D scenes. While geometric deep le ...