English

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

Computer Vision and Pattern Recognition 2026-03-06 v3 Artificial Intelligence

Abstract

Existing research on 3D Large Language Models (LLMs) still struggles to achieve grounded question-answering, primarily due to the under-exploration of the mechanism of human-like scene-object grounded reasoning. This paper bridges the gap by presenting a novel framework. We first introduce a grounded 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 enable such a method, we develop SCENECOT-185K, the first large-scale grounded CoT reasoning dataset, consisting of 185K high-quality instances. Extensive experiments across various complex 3D scene reasoning benchmarks demonstrate that our new framework achieves strong performance with high grounding-QA coherence. To the best of our knowledge, this is the first successful application of CoT reasoning to 3D scene understanding, enabling step-by-step human-like reasoning and showing potential for extension to broader 3D scene understanding scenarios.

Keywords

Cite

@article{arxiv.2510.16714,
  title  = {SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes},
  author = {Xiongkun Linghu and Jiangyong Huang and Ziyu Zhu and Baoxiong Jia and Siyuan Huang},
  journal= {arXiv preprint arXiv:2510.16714},
  year   = {2026}
}

Comments

Accepted by ICLR 2026. Project page: https://scenecot.github.io/