The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts
This work addresses the challenge of 3D shape generation for computer graphics and design, offering a novel approach that is incremental in its use of graph neural networks and optimization.
The paper tackles the problem of generating novel 3D shapes from existing parts by introducing a contact-based reasoning method that uses slot graphs to assemble shapes without semantic labels or complete part geometries, resulting in shapes that outperform existing approaches in quality, diversity, and structural complexity.
We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning. Our method represents each shape as a graph of ``slots,'' where each slot is a region of contact between two shape parts. Based on this representation, we design a graph-neural-network-based model for generating new slot graphs and retrieving compatible parts, as well as a gradient-descent-based optimization scheme for assembling the retrieved parts into a complete shape that respects the generated slot graph. This approach does not require any semantic part labels; interestingly, it also does not require complete part geometries -- reasoning about the slots proves sufficient to generate novel, high-quality 3D shapes. We demonstrate that our method generates shapes that outperform existing modeling-by-assembly approaches regarding quality, diversity, and structural complexity.