Timezone: »

ShapeFlow: Learnable Deformation Flows Among 3D Shapes
Chiyu Jiang · Jingwei Huang · Andrea Tagliasacchi · Leonidas Guibas

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1301

We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. ShapeFlow allows learning a multi-template deformation space that is agnostic to shape topology, yet preserves fine geometric details. Different from a generative space where a latent vector is directly decoded into a shape, a deformation space decodes a vector into a continuous flow that can advect a source shape towards a target. Such a space naturally allows the disentanglement of geometric style (coming from the source) and structural pose (conforming to the target). We parametrize the deformation between geometries as a learned continuous flow field via a neural network and show that such deformations can be guaranteed to have desirable properties, such as bijectivity, freedom from self-intersections, or volume preservation. We illustrate the effectiveness of this learned deformation space for various downstream applications, including shape generation via deformation, geometric style transfer, unsupervised learning of a consistent parameterization for entire classes of shapes, and shape interpolation.

Author Information

Max Jiang (UC Berkeley)
Jingwei Huang (Stanford University)
Andrea Tagliasacchi (Google Research, Brain)
Leonidas Guibas (stanford.edu)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors