SyncAI.news, a Varaisys broadcasting
CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments
BY

Boao Yu, Yingzhen Nie, Yue Hu, Zhengqiu Zhu, Rusheng Ju

· 1 min read

ResearcharXiv cs.CV

CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments

arXiv:2609.32427v1 Announce Type: new Abstract: CityToolVQA addresses the weak performance of Vision-Language Models (VLMs) on quantitative tasks in urban low-altitude visual question answering. We divide the seven tasks into qualitative and quantitative groups: qualitative questions are answered directly by the VLM, whereas quantitative questions are handled by an external visual-geometric toolchain that performs object grounding, segmentation, depth back-projection, and spatial computation. The toolchain can be attached to different VLMs in a zero-shot manner; a Depth-Assisted Prompt Inference (DAPI) fallback is triggered when the main-chain detection is invalid or unreliable, and CityToolVQA-SFT adapts the 8B backbone to tool-conditioned inputs. On the 73,324-question Open3D-VQA-v2 test set, CityToolVQA-SFT (Qwen3-VL-8B) reaches 67.6% overall accuracy, and attaching the toolchain to ten open-source VLMs improves quantitative-task accuracy by 12.7-36.9 percentage points. These results indicate that externalizing explicit 3D geometric computation effectively complements the limited ability of RGB-only VLMs to estimate metric distances and object sizes.

Original source

This story was published by arXiv cs.CV and written by Boao Yu, Yingzhen Nie, Yue Hu, Zhengqiu Zhu, Rusheng Ju. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News