Learning Shape Abstractions by Assembling Volumetric Primitives
This work addresses shape abstraction and manipulation for 3D modeling and computer vision applications, presenting a novel method but with incremental improvements in interpretability.
The paper tackles the problem of abstracting complex 3D shapes by learning to assemble them from volumetric primitives, resulting in geometrically interpretable explanations, consistent parsing across shape collections, and an interpretable shape similarity measure.
We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives. In addition to generating simple and geometrically interpretable explanations of 3D objects, our framework also allows us to automatically discover and exploit consistent structure in the data. We demonstrate that using our method allows predicting shape representations which can be leveraged for obtaining a consistent parsing across the instances of a shape collection and constructing an interpretable shape similarity measure. We also examine applications for image-based prediction as well as shape manipulation.