
HZ
Hongpei Zheng, Shijie Li, Lin Qian, Zhenghao Li, Qijun Yang, Yanran Li, Hujun Yin
· 1 min read
ResearcharXiv cs.CV
Think, Then Look: Active Spatial Reasoning for House-Scale 3D Scene Understanding
arXiv:2512.03284v2 Announce Type: replace
Abstract: Spatial reasoning in large-scale 3D environments remains challenging for current vision--language models, which are typically constrained to room-scale scenarios. We formalize Active House-Scale Spatial Reasoning (AHSR), a new paradigm in which a model reasons over a pre-built house-scale 3D map via virtual spatial tool invocations to answer spatial questions, without exhaustive scene-wide processing. To support AHSR research, we introduce H$^2$U3D (Holistic House Understanding in 3D), the first benchmark targeting house-scale 3D scene understanding, featuring environments with an average aggregate floor area of 250.8 m$^2$ and up to three floors, together with hierarchical coarse-to-fine visual representations. Building on H$^2$U3D, we propose SpatialReasoner, an AHSR framework trained via supervised fine-tuning with self-correction, followed by reinforcement learning with a task-aware adaptive exploration reward. SpatialReasoner achieves state-of-the-art performance on H$^2$U3D with 64.9% overall accuracy, outperforming strong baselines including GPT-5.4 and Gemini-3.5-Flash, and generalizes effectively to MT-HM3D and HM-EQA. These results demonstrate the clear advantage of active map-directed exploration over passive scene-wide processing in house-scale 3D understanding.
Original source
This story was published by arXiv cs.CV and written by Hongpei Zheng, Shijie Li, Lin Qian, Zhenghao Li, Qijun Yang, Yanran Li, Hujun Yin. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


