SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes

Xiongkun Linghu, Jiangyong Huang, Ziyu Zhu, Baoxiong Jia, Siyuan Huang

 

 

SceneCOT: We propose a Chain-of-Thought reasoning method in 3D scenes (SceneCOT), decoupling a complex reasoning task into simpler and manageable problems, and building corresponding visual clues based on multimodal expert modules. To our knowledge, this is the first attempt to successfully implement the COT technique for achieving human-like step-by-step reasoning for 3D scene understanding, where we show great potential in extending it to a wider range of 3D scene understanding scenarios.

SceneCOT Framework

SceneCOT achieves great performance on MSQA, and Beacon3D, demonstrating the effectiveness of our reasoning framework. Especially, our method significanlty enhances the performance on counting, the most challenging task in MSQA. Our method also significanlty outperforms previous methods by a large margin in Beacon3D.

🔥 News

• [2025-6] We released the webpage of SceneCOT.

📝 TODO List

• Arxiv paper
• Evaluation code
• Model weights
• SceneCOT-185K dataset
• Training code

BibTex

If you find our work helpful, please consider citing us:

@article{linghu2025scenecot,
  title={SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes},
  author={Linghu, Xiongkun and Huang, Jiangyong and Zhu, Ziyu and Jia, Baoxiong and Huang, Siyuan},
  journal={arXiv preprint arXiv:2510.16714},
  year={2025}
}