GRASS: Generative Recursive Autoencoders for Shape Structures

Understand

We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures.

• Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry.
• We develop a recursive neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code.
• The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy.