# MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

arXiv: https://arxiv.org/abs/2508.14879 · HTML: https://mlsanity.com/paper/2508.14879/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 42 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 30 of 35)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [SDM-NET: Deep Generative Network for Structured Deformable Mesh](https://mlsanity.com/paper/1908.04520/) (2019)
- [SAMPart3D: Segment Any Part in 3D Objects](https://mlsanity.com/paper/2411.07184/) (2024)
- [Hierarchical Neural Coding for Controllable CAD Model Generation](https://mlsanity.com/paper/2307.00149/) (2023)
- [SolidGen: An Autoregressive Model for Direct B-rep Synthesis](https://mlsanity.com/paper/2203.13944/) (2022)
- [Learning to Infer and Execute 3D Shape Programs](https://mlsanity.com/paper/1901.02875/) (2019)
- [SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2303.12236/) (2023)
- [DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning](https://mlsanity.com/paper/2503.15265/) (2025)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [SATR: Zero-Shot Semantic Segmentation of 3D Shapes](https://mlsanity.com/paper/2304.04909/) (2023)
- [PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models](https://mlsanity.com/paper/2412.18608/) (2024)
- [Part123: Part-aware 3D Reconstruction from a Single-view Image](https://mlsanity.com/paper/2405.16888/) (2024)
- [VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes](https://mlsanity.com/paper/1809.00226/) (2018)
- [PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation](https://mlsanity.com/paper/2312.03015/) (2023)
- [Segment Any Mesh](https://mlsanity.com/paper/2408.13679/) (2024)
- [DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion](https://mlsanity.com/paper/2305.01921/) (2023)
- [PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation](https://mlsanity.com/paper/2312.04016/) (2023)
- [ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives](https://mlsanity.com/paper/2305.05661/) (2023)
- [MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis](https://mlsanity.com/paper/2407.13675/) (2024)
- [PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate Distributions](https://mlsanity.com/paper/2011.13045/) (2020)
- [ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation](https://mlsanity.com/paper/2311.14262/) (2023)

## Built on by (most cited first, 19 of 19)

- [X-Part: high fidelity and structure coherent shape decomposition](https://mlsanity.com/paper/2509.08643/) (2025)
- [Code2Worlds: Empowering Coding LLMs for 4D World Generation](https://mlsanity.com/paper/2602.11757/) (2026)
- [SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects](https://mlsanity.com/paper/2605.19587/) (2026)
- [Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models](https://mlsanity.com/paper/2606.02580/) (2026)
- [UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents](https://mlsanity.com/paper/2512.09435/) (2025)
- [VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation](https://mlsanity.com/paper/2604.02580/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models](https://mlsanity.com/paper/2601.21798/) (2026)
- [Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction](https://mlsanity.com/paper/2512.05597/) (2025)
- [3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis](https://mlsanity.com/paper/2606.10478/) (2026)
- [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (2026)
- [CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning](https://mlsanity.com/paper/2610.04262/) (2026)
- [Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training](https://mlsanity.com/paper/2601.03256/) (2026)
- [Design-Specification Tiling for ICL-based CAD Code Generation](https://mlsanity.com/paper/2603.12712/) (2026)
- [AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building models](https://mlsanity.com/paper/2609.28061/) (2026)
- [Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation](https://mlsanity.com/paper/2609.36918/) (2026)
- [FACT: Fidelity-Aware Construction of Articulated Twins](https://mlsanity.com/paper/2609.37067/) (2026)
- [ViewStruct: View-Grounded Articulation and Connectivity Inference](https://mlsanity.com/paper/2610.16793/) (2026)
- [Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation](https://mlsanity.com/paper/2610.17651/) (2026)

## Abstract (arXiv)

Reconstructing 3D objects into editable programs is pivotal for applications like reverse engineering and shape editing. However, existing methods often rely on limited domain-specific languages (DSLs) and small-scale datasets, restricting their ability to model complex geometries and structures. To address these challenges, we introduce MeshCoder, a novel framework that reconstructs complex 3D objects from point clouds into editable Blender Python scripts. We develop a comprehensive set of expressive Blender Python APIs capable of synthesizing intricate geometries. Leveraging these APIs, we construct a large-scale paired object-code dataset, where the code for each object is decomposed into distinct semantic parts. Subsequently, we train a multimodal large language model (LLM) that translates 3D point cloud into executable Blender Python scripts. Our approach not only achieves superior performance in shape-to-code reconstruction tasks but also facilitates intuitive geometric and topological editing through convenient code modifications. Furthermore, our code-based representation enhances the reasoning capabilities of LLMs in 3D shape understanding tasks. Together, these contributions establish MeshCoder as a powerful and flexible solution for programmatic 3D shape reconstruction and understanding. The project homepage is available at hrefhttps://daibingquan.github.io/MeshCoderthis link.