# Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI

arXiv: https://arxiv.org/abs/2309.06379 · HTML: https://mlsanity.com/paper/2309.06379/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 60 references that are in the map.
- First posted on arXiv 12 Sep 2023.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [Differentiable Rendering: A Survey](https://mlsanity.com/paper/2006.12057/) (2020)
- [3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding](https://mlsanity.com/paper/2103.16397/) (2021)
- [TextDeformer: Geometry Manipulation using Text Guidance](https://mlsanity.com/paper/2304.13348/) (2023)
- [MeshCNN: A Network with an Edge](https://mlsanity.com/paper/1809.05910/) (2018)
- [Texturify: Generating Textures on 3D Shape Surfaces](https://mlsanity.com/paper/2204.02411/) (2022)
- [3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations](https://mlsanity.com/paper/2108.12958/) (2021)
- [PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation](https://mlsanity.com/paper/1903.00709/) (2019)
- [3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions](https://mlsanity.com/paper/2212.11263/) (2022)
- [SliceHub: Augmenting Shared 3D Model Repositories with Slicing Results for 3D Printing](https://mlsanity.com/paper/2109.14722/) (2021)
- [Autocomplete Textures for 3D Printing](https://mlsanity.com/paper/1703.05700/) (2017)

## Built on by (most cited first, 11 of 11)

- [DreamGarden: A Designer Assistant for Growing Games from a Single Prompt](https://mlsanity.com/paper/2410.01791/) (2024)
- [Shaping Realities: Enhancing 3D Generative AI with Fabrication Constraints](https://mlsanity.com/paper/2404.10142/) (2024)
- [Speech to Reality: On-Demand Production using Natural Language, 3D Generative AI, and Discrete Robotic Assembly](https://mlsanity.com/paper/2409.18390/) (2024)
- [TactStyle: Generating Tactile Textures with Generative AI for Digital Fabrication](https://mlsanity.com/paper/2503.02007/) (2025)
- [Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models](https://mlsanity.com/paper/2511.02162/) (2025)
- [Dreamcrafter: Immersive Editing of 3D Radiance Fields Through Flexible, Generative Inputs and Outputs](https://mlsanity.com/paper/2512.20129/) (2025)
- [MechStyle: Augmenting Generative AI with Mechanical Simulation to Create Stylized and Structurally Viable 3D Models](https://mlsanity.com/paper/2509.20571/) (2025)
- [Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization](https://mlsanity.com/paper/2506.20056/) (2025)
- [Compos3D: Interactive Part-Based Composition for Creative Control in Generative 3D Models](https://mlsanity.com/paper/2607.12193/) (2026)
- [SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects](https://mlsanity.com/paper/2608.18560/) (2026)
- [InstructMesh: Selective Refinement of Generative 3D Models for Fabrication](https://mlsanity.com/paper/2608.28534/) (2026)

## Abstract (arXiv)

With recent advances in Generative AI, it is becoming easier to automatically manipulate 3D models. However, current methods tend to apply edits to models globally, which risks compromising the intended functionality of the 3D model when fabricated in the physical world. For example, modifying functional segments in 3D models, such as the base of a vase, could break the original functionality of the model, thus causing the vase to fall over. We introduce a method for automatically segmenting 3D models into functional and aesthetic elements. This method allows users to selectively modify aesthetic segments of 3D models, without affecting the functional segments. To develop this method we first create a taxonomy of functionality in 3D models by qualitatively analyzing 1000 models sourced from a popular 3D printing repository, Thingiverse. With this taxonomy, we develop a semi-automatic classification method to decompose 3D models into functional and aesthetic elements. We propose a system called Style2Fab that allows users to selectively stylize 3D models without compromising their functionality. We evaluate the effectiveness of our classification method compared to human-annotated data, and demonstrate the utility of Style2Fab with a user study to show that functionality-aware segmentation helps preserve model functionality.