# COALESCE: Component Assembly by Learning to Synthesize Connections

arXiv: https://arxiv.org/abs/2008.01936 · HTML: https://mlsanity.com/paper/2008.01936/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2020.

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

- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [Flexible Isosurface Extraction for Gradient-Based Mesh Optimization](https://mlsanity.com/paper/2308.05371/) (2023)
- [JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints](https://mlsanity.com/paper/2111.12772/) (2021)
- [3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models](https://mlsanity.com/paper/2212.00842/) (2022)
- [Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors](https://mlsanity.com/paper/2205.14886/) (2022)
- [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)
- [PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision](https://mlsanity.com/paper/2303.09554/) (2023)
- [DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion](https://mlsanity.com/paper/2305.01921/) (2023)
- [Jigsaw: Learning to Assemble Multiple Fractured Objects](https://mlsanity.com/paper/2305.17975/) (2023)
- [SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation](https://mlsanity.com/paper/2201.13168/) (2022)
- [Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly](https://mlsanity.com/paper/2309.06810/) (2023)
- [Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation](https://mlsanity.com/paper/2302.00190/) (2023)
- [Category-Level Multi-Part Multi-Joint 3D Shape Assembly](https://mlsanity.com/paper/2303.06163/) (2023)
- [NeuForm: Adaptive Overfitting for Neural Shape Editing](https://mlsanity.com/paper/2207.08890/) (2022)
- [PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify](https://mlsanity.com/paper/2406.00259/) (2024)
- [Geometric Deep Learning for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2402.17695/) (2024)
- [AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies](https://mlsanity.com/paper/2105.12238/) (2021)
- [Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation](https://mlsanity.com/paper/2504.06961/) (2025)
- [An Implicit Parametric Morphable Dental Model](https://mlsanity.com/paper/2211.11402/) (2022)
- [TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation](https://mlsanity.com/paper/2210.05735/) (2022)
- [CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization](https://mlsanity.com/paper/2402.02313/) (2024)
- [The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts](https://mlsanity.com/paper/2112.00584/) (2021)
- [Manual-PA: Learning 3D Part Assembly from Instruction Diagrams](https://mlsanity.com/paper/2411.18011/) (2024)
- [Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection](https://mlsanity.com/paper/2312.11867/) (2023)
- [Attention-based Part Assembly for 3D Volumetric Shape Modeling](https://mlsanity.com/paper/2304.10986/) (2023)
- [Controllable Shape Modeling with Neural Generalized Cylinder](https://mlsanity.com/paper/2410.03675/) (2024)
- [Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach](https://mlsanity.com/paper/2108.02161/) (2021)
- [Diverse Part Synthesis for 3D Shape Creation](https://mlsanity.com/paper/2401.09384/) (2024)
- [CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation](https://mlsanity.com/paper/2607.16577/) (2026)

## Abstract (arXiv)

We introduce COALESCE, the first data-driven framework for component-based shape assembly which employs deep learning to synthesize part connections. To handle geometric and topological mismatches between parts, we remove the mismatched portions via erosion, and rely on a joint synthesis step, which is learned from data, to fill the gap and arrive at a natural and plausible part joint. Given a set of input parts extracted from different objects, COALESCE automatically aligns them and synthesizes plausible joints to connect the parts into a coherent 3D object represented by a mesh. The joint synthesis network, designed to focus on joint regions, reconstructs the surface between the parts by predicting an implicit shape representation that agrees with existing parts, while generating a smooth and topologically meaningful connection. We employ test-time optimization to further ensure that the synthesized joint region closely aligns with the input parts to create realistic component assemblies from diverse input parts. We demonstrate that our method significantly outperforms prior approaches including baseline deep models for 3D shape synthesis, as well as state-of-the-art methods for shape completion.