EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
This enables more flexible 3D shape editing and generation for computer graphics and vision applications, though it builds incrementally on existing VAE frameworks.
The paper tackles unsupervised parts-aware 3D point cloud generation by modifying a Variational Auto-Encoder to create a joint model that decomposes shapes into disentangled part representations with shape primitives and canonical transformations. This approach achieves state-of-the-art results on the ShapeNet dataset without requiring pre-segmented data.
This paper tackles the problem of parts-aware point cloud generation. Unlike existing works which require the point cloud to be segmented into parts a priori, our parts-aware editing and generation are performed in an unsupervised manner. We achieve this with a simple modification of the Variational Auto-Encoder which yields a joint model of the point cloud itself along with a schematic representation of it as a combination of shape primitives. In particular, we introduce a latent representation of the point cloud which can be decomposed into a disentangled representation for each part of the shape. These parts are in turn disentangled into both a shape primitive and a point cloud representation, along with a standardising transformation to a canonical coordinate system. The dependencies between our standardising transformations preserve the spatial dependencies between the parts in a manner that allows meaningful parts-aware point cloud generation and shape editing. In addition to the flexibility afforded by our disentangled representation, the inductive bias introduced by our joint modeling approach yields state-of-the-art experimental results on the ShapeNet dataset.