This repository will contain the official implementation of the paper: SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge. SPARK is a novel framework that integrates VLM-guided part-level and global image guidance with diffusion transformers to produce high-quality articulated object reconstructions.

Feel free to open an issue if you have any questions or suggestions.

• 2025-12-01: SPARK is on arXiv.

• Provide a HuggingFace🤗 demo.
• Release inference scripts and pretrained checkpoints.
• Release training code and data preprocessing scripts.
• Release preprocessed dataset.

If you find our work helpful, please consider citing:

@misc{he2025spark,
  title={SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge}, 
  author={Yumeng He and Ying Jiang and Jiayin Lu and Yin Yang and Chenfanfu Jiang},
  year={2025},
  eprint={2512.01629},
  url={https://arxiv.org/abs/2512.01629}
}