Predicting shapes as implicit functions

Predicting signed-distance functions from points clouds using neural networks

References

Very similar ideas are presented in the following papers (all put online between December 2018 and January 2019!):

Occupancy Networks: Learning 3D Reconstruction in Function Space

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Deep Level Sets: Implicit Surface Representations for 3D Shape Inference

Learning Implicit Fields for Generative Shape Modeling