VoronoiNet: General Functional Approximators with Local Support
This work addresses shape reconstruction in graphics, but it appears incremental as it builds on existing implicit occupancy networks with preliminary results.
The authors tackled the problem of generating detailed 2D and 3D shape reconstructions by embedding a differentiable Voronoi diagram into a generative deep network, achieving more detailed reconstructions with a highly compact latent embedding.
Voronoi diagrams are highly compact representations that are used in various Graphics applications. In this work, we show how to embed a differentiable version of it -- via a novel deep architecture -- into a generative deep network. By doing so, we achieve a highly compact latent embedding that is able to provide much more detailed reconstructions, both in 2D and 3D, for various shapes. In this tech report, we introduce our representation and present a set of preliminary results comparing it with recently proposed implicit occupancy networks.