English

SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding

Computer Vision and Pattern Recognition 2025-12-04 v1

Abstract

Spatial reasoning in large-scale 3D environments remains challenging for current vision-language models, which are typically constrained to room-scale scenarios. We introduce H2^2U3D (Holistic House Understanding in 3D), a 3D visual question answering dataset designed for house-scale scene understanding. H2^2U3D features multi-floor environments spanning up to three floors and 10-20 rooms, covering more than 300 m2^2. Through an automated annotation pipeline, it constructs hierarchical coarse-to-fine visual representations and generates diverse question-answer pairs with chain-of-thought annotations. We further propose SpatialReasoner, an active perception framework that autonomously invokes spatial tools to explore 3D scenes based on textual queries. SpatialReasoner is trained through a two-stage strategy: a supervised cold start followed by reinforcement learning with an adaptive exploration reward that promotes efficient exploration while discouraging redundant operations. Extensive experiments demonstrate that SpatialReasoner achieves state-of-the-art performance on H2^2U3D, outperforming strong baselines including GPT-4o and Gemini-2.5-Pro. Notably, our method attains superior results while using only 3-4 images in total on average, compared to baselines requiring 16+ images, highlighting the effectiveness of our coarse-to-fine active exploration paradigm.

Keywords

Cite

@article{arxiv.2512.03284,
  title  = {SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding},
  author = {Hongpei Zheng and Shijie Li and Yanran Li and Hujun Yin},
  journal= {arXiv preprint arXiv:2512.03284},
  year   = {2025}
}
R2 v1 2026-07-01T08:06:45.520Z