# The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts

arXiv: https://arxiv.org/abs/2112.00584 · HTML: https://mlsanity.com/paper/2112.00584/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [SDM-NET: Deep Generative Network for Structured Deformable Mesh](https://mlsanity.com/paper/1908.04520/) (2019)
- [3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks](https://mlsanity.com/paper/1708.01648/) (2017)
- [Generative 3D Part Assembly via Dynamic Graph Learning](https://mlsanity.com/paper/2006.07793/) (2020)
- [COALESCE: Component Assembly by Learning to Synthesize Connections](https://mlsanity.com/paper/2008.01936/) (2020)

## Built on by (most cited first, 7 of 7)

- [SPAFormer: Sequential 3D Part Assembly with Transformers](https://mlsanity.com/paper/2403.05874/) (2024)
- [NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments](https://mlsanity.com/paper/2201.13063/) (2022)
- [Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly](https://mlsanity.com/paper/2303.01999/) (2023)
- [Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection](https://mlsanity.com/paper/2312.11867/) (2023)
- [StructRe: Rewriting for Structured Shape Modeling](https://mlsanity.com/paper/2311.17510/) (2023)
- [Functionalization via Structure Completion and Motion Rectification](https://mlsanity.com/paper/2605.18010/) (2026)
- [PART: Learning 3D Part Assembly and Retrieval with Transformers](https://mlsanity.com/paper/2609.19872/) (2026)

## Abstract (arXiv)

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.