视觉语言模型距离视觉空间智能还有多远？基于基准测试的视角

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective

September 23, 2025

作者: Songsong Yu, Yuxin Chen, Hao Ju, Lianjie Jia, Fuxi Zhang, Shaofei Huang, Yuhan Wu, Rundi Cui, Binghao Ran, Zaibin Zhang, Zhedong Zheng, Zhipeng Zhang, Yifan Wang, Lin Song, Lijun Wang, Yanwei Li, Ying Shan, Huchuan Lu

cs.AI

摘要

视觉空间推理（Visual Spatial Reasoning, VSR）是人类核心认知能力之一，也是推动具身智能与自主系统发展的关键需求。尽管视觉-语言模型（Vision-Language Models, VLMs）近期取得了显著进展，但由于三维空间表示与推理的复杂性，实现人类水平的VSR仍面临巨大挑战。本文对VLMs中的VSR进行了系统性研究，涵盖了输入模态、模型架构、训练策略及推理机制等方面现有方法的综述。此外，我们将空间智能划分为三个能力层次，即基础感知、空间理解与空间规划，并构建了SIBench——一个包含近20个开源数据集、覆盖23种任务场景的空间智能基准。通过对当前最先进VLMs的实验分析，我们发现模型在感知与推理之间存在显著差距：模型在基础感知任务上表现尚可，但在理解与规划任务上持续表现不佳，特别是在数值估计、多视角推理、时间动态及空间想象等方面。这些发现凸显了实现空间智能所面临的重大挑战，同时为未来研究提供了系统性的路线图与全面的基准。本研究的相关资源可通过https://sibench.github.io/Awesome-Visual-Spatial-Reasoning/访问。

English

Visual Spatial Reasoning (VSR) is a core human cognitive ability and a critical requirement for advancing embodied intelligence and autonomous systems. Despite recent progress in Vision-Language Models (VLMs), achieving human-level VSR remains highly challenging due to the complexity of representing and reasoning over three-dimensional space. In this paper, we present a systematic investigation of VSR in VLMs, encompassing a review of existing methodologies across input modalities, model architectures, training strategies, and reasoning mechanisms. Furthermore, we categorize spatial intelligence into three levels of capability, ie, basic perception, spatial understanding, spatial planning, and curate SIBench, a spatial intelligence benchmark encompassing nearly 20 open-source datasets across 23 task settings. Experiments with state-of-the-art VLMs reveal a pronounced gap between perception and reasoning, as models show competence in basic perceptual tasks but consistently underperform in understanding and planning tasks, particularly in numerical estimation, multi-view reasoning, temporal dynamics, and spatial imagination. These findings underscore the substantial challenges that remain in achieving spatial intelligence, while providing both a systematic roadmap and a comprehensive benchmark to drive future research in the field. The related resources of this study are accessible at https://sibench.github.io/Awesome-Visual-Spatial-Reasoning/.