We consider the problem of scaling deep generative shape models to high-resolution. Drawing motivation from the canonical view representation of objects, we introduce a novel method for the fast up-sampling of 3D objects in voxel space through networks that perform super-resolution on the six orthographic depth projections. This allows us to generate high-resolution objects with more efficient scaling than methods which work directly in 3D. We decompose the problem of 2D depth super-resolution into silhouette and depth prediction to capture both structure and fine detail. This allows our method to generate sharp edges more easily than an individual network. We evaluate our work on multiple experiments concerning high-resolution 3D objects, and show our system is capable of accurately predicting novel objects at resolutions as large as 512x512x512 -- the highest resolution reported for this task. We achieve state-of-the-art performance on 3D object reconstruction from RGB images on the ShapeNet dataset, and further demonstrate the first effective 3D super-resolution method.
Edward Smith (McGill University)
Scott Fujimoto (McGill University)
David Meger (University of British Columbia)
More from the Same Authors
2019 Poster: Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer »
Wenzheng Chen · Huan Ling · Jun Gao · Edward Smith · Jaakko Lehtinen · Alec Jacobson · Sanja Fidler