# Learning Part Generation and Assembly for Structure-aware Shape Synthesis

arXiv: https://arxiv.org/abs/1906.06693 · HTML: https://mlsanity.com/paper/1906.06693/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2019.

## Built on by (most cited first, 30 of 36)

- [SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation](https://mlsanity.com/paper/2206.12055/) (2022)
- [JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints](https://mlsanity.com/paper/2111.12772/) (2021)
- [FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly](https://mlsanity.com/paper/2308.10608/) (2023)
- [SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects](https://mlsanity.com/paper/2410.16499/) (2024)
- [Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds](https://mlsanity.com/paper/2106.03437/) (2021)
- [Breaking Bad: A Dataset for Geometric Fracture and Reassembly](https://mlsanity.com/paper/2210.11463/) (2022)
- [RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly](https://mlsanity.com/paper/2107.12859/) (2021)
- [DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion](https://mlsanity.com/paper/2305.01921/) (2023)
- [NAP: Neural 3D Articulation Prior](https://mlsanity.com/paper/2305.16315/) (2023)
- [Category-Level Multi-Part Multi-Joint 3D Shape Assembly](https://mlsanity.com/paper/2303.06163/) (2023)
- [3D Part Assembly Generation with Instance Encoded Transformer](https://mlsanity.com/paper/2207.01779/) (2022)
- [ANISE: Assembly-based Neural Implicit Surface rEconstruction](https://mlsanity.com/paper/2205.13682/) (2022)
- [PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify](https://mlsanity.com/paper/2406.00259/) (2024)
- [GARF: Learning Generalizable 3D Reassembly for Real-World Fractures](https://mlsanity.com/paper/2504.05400/) (2025)
- [SPAFormer: Sequential 3D Part Assembly with Transformers](https://mlsanity.com/paper/2403.05874/) (2024)
- [ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents](https://mlsanity.com/paper/2510.21432/) (2025)
- [Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors](https://mlsanity.com/paper/2104.00476/) (2021)
- [3D Geometric Shape Assembly via Efficient Point Cloud Matching](https://mlsanity.com/paper/2407.10542/) (2024)
- [A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts](https://mlsanity.com/paper/2410.14770/) (2024)
- [A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras](https://mlsanity.com/paper/2210.01607/) (2022)
- [Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase](https://mlsanity.com/paper/2306.12423/) (2023)
- [Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection](https://mlsanity.com/paper/2312.11867/) (2023)
- [Hierarchical Part-based Generative Model for Realistic 3D Blood Vessel](https://mlsanity.com/paper/2507.15223/) (2025)
- [Material Prediction for Design Automation Using Graph Representation Learning](https://mlsanity.com/paper/2209.12793/) (2022)
- [Attention-based Part Assembly for 3D Volumetric Shape Modeling](https://mlsanity.com/paper/2304.10986/) (2023)
- [A Survey of Methods for Converting Unstructured Data to CSG Models](https://mlsanity.com/paper/2305.01220/) (2023)
- [GenUDC: High Quality 3D Mesh Generation with Unsigned Dual Contouring Representation](https://mlsanity.com/paper/2410.17802/) (2024)
- [Combinative Matching for Geometric Shape Assembly](https://mlsanity.com/paper/2508.09780/) (2025)
- [Deep Generative Models on 3D Representations: A Survey](https://mlsanity.com/paper/2210.15663/) (2022)
- [3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability](https://mlsanity.com/paper/2307.14051/) (2023)

## Abstract (arXiv)

Learning powerful deep generative models for 3D shape synthesis is largely hindered by the difficulty in ensuring plausibility encompassing correct topology and reasonable geometry. Indeed, learning the distribution of plausible 3D shapes seems a daunting task for the holistic approaches, given the significant topological variations of 3D objects even within the same category. Enlightened by the fact that 3D shape structure is characterized as part composition and placement, we propose to model 3D shape variations with a part-aware deep generative network, coined as PAGENet. The network is composed of an array of per-part VAE-GANs, generating semantic parts composing a complete shape, followed by a part assembly module that estimates a transformation for each part to correlate and assemble them into a plausible structure. Through delegating the learning of part composition and part placement into separate networks, the difficulty of modeling structural variations of 3D shapes is greatly reduced. We demonstrate through both qualitative and quantitative evaluations that PAGENet generates 3D shapes with plausible, diverse and detailed structure, and show two applications, i.e., semantic shape segmentation and part-based shape editing.