trizhi/cadevolve

---
license: apache-2.0
pretty_name: CADEvolve
dataset_type: synthetic
---

# CADEvolve: Creating Realistic CAD via Program Evolution

**CADEvolve** is a synthetic dataset for **CAD reverse engineering** built around **executable CadQuery programs**. It is produced by the CADEvolve pipeline, which evolves a small set of primitives into **8k complex parametric generators**, and then expands them into a large corpus of CAD programs (≈1.3M scripts) exercising a broad CadQuery operation set.

- Paper: [arXiv:2602.16317](https://arxiv.org/abs/2602.16317)
- Code: [GitHub](https://github.com/zhemdi/CADEvolve)

## Repository structure

This dataset repo contains **three top-level folders**:

### `CADEvolve-G/`
- `parametric_generators.json`: the library of **parametric generator programs** (the evolved generator set).
- `embeddings/`: precomputed embeddings for retrieval / indexing (optional utility).

### `CADEvolve-P/`
Three subfolders with **`.py` CAD programs**:
- `ABC-P/`
- `CADEvolve-P-core/`
- `ShapeNet-P/`

### `CADEvolve-C/`
Three subfolders with **`.py` CAD programs**:
- `ABC-C/`
- `CADEvolve-C-core/`
- `ShapeNet-C/`

## Citation

```bibtex
@article{elistratov2026cadevolve,
title={CADEvolve: Creating Realistic CAD via Program Evolution},
author={Elistratov, Maksim and Barannikov, Marina and Ivanov, Gregory and Khrulkov, Valentin and Konushin, Anton and Kuznetsov, Andrey and Zhemchuzhnikov, Dmitrii},
journal={arXiv preprint arXiv:2602.16317},
year={2026}
}

license: apache-2.0
pretty_name: CADEvolve
dataset_type: synthetic
---

# CADEvolve：通过程序演化生成逼真CAD模型

**CADEvolve**是一款面向**CAD逆向工程（CAD reverse engineering）**的合成数据集，其核心依托可执行的CadQuery程序构建。该数据集由CADEvolve流水线生成：首先将少量基础图元演化为8000个（8k）复杂参数化生成器，随后将这些生成器扩展为覆盖广泛CadQuery操作集的大规模CAD程序语料库（约130万条脚本）。

- 论文：[arXiv:2602.16317](https://arxiv.org/abs/2602.16317)
- 代码：[GitHub](https://github.com/zhemdi/CADEvolve)

## 仓库结构

本数据集仓库包含三个顶级文件夹：

### `CADEvolve-G/`
- `parametric_generators.json`：参数化生成器程序库（即演化得到的生成器集合）。
- `embeddings/`：用于检索或索引的预计算嵌入向量（可选工具组件）。

### `CADEvolve-P/`
包含三个子文件夹，均存储`.py`格式的CAD程序：
- `ABC-P/`
- `CADEvolve-P-core/`
- `ShapeNet-P/`

### `CADEvolve-C/`
包含三个子文件夹，均存储`.py`格式的CAD程序：
- `ABC-C/`
- `CADEvolve-C-core/`
- `ShapeNet-C/`

## 引用

bibtex
@article{elistratov2026cadevolve,
title={CADEvolve: Creating Realistic CAD via Program Evolution},
author={Elistratov, Maksim and Barannikov, Marina and Ivanov, Gregory and Khrulkov, Valentin and Konushin, Anton and Kuznetsov, Andrey and Zhemchuzhnikov, Dmitrii},
journal={arXiv preprint arXiv:2602.16317},
year={2026}
}