arXiv 2602.209012026-02-24cs.CVcs.LG

SpatiaLQA: 一个评估视觉-语言模型空间逻辑推理能力的基准

SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models

Zhejiang University（浙江大学）；The University of Sydney（悉尼大学）；ManyCore；State Key Laboratory of Blockchain and Security, Zhejiang University（浙江大学区块链与安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）

Yuechen Xie, Xiaoyan Zhang, Yicheng Shan, Hao Zhu, Rui Tang, Rong Wei, Mingli Song, Yuanyu Wan, Jie Song

备注：: Accepted by CVPR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

SpatiaLQA提出了一种评估视觉-语言模型空间逻辑推理能力的基准，通过递归场景图辅助推理方法提升模型在复杂场景中的推理能力。

摘要：

视觉-语言模型（VLMs）由于其出色的理解和推理能力，已被越来越多地应用于现实世界场景。尽管VLMs已经在常见的视觉问答和逻辑推理方面展示了令人印象深刻的能力，但它们仍然缺乏在复杂现实环境中做出合理决策的能力。我们将这种能力定义为空间逻辑推理，这不仅需要理解复杂场景中物体之间的空间关系，还需要理解多步骤任务中步骤之间的逻辑依赖性。为了弥合这一差距，我们引入了空间逻辑问答（SpatiaLQA），这是一个旨在评估VLMs空间逻辑推理能力的基准。SpatiaLQA包含9,605对问题答案，来源于241个现实世界的室内场景。我们在41种主流VLMs上进行了广泛的实验，结果表明，即使是最先进的模型仍然在空间逻辑推理上遇到困难。为了解决这个问题，我们提出了一种称为递归场景图辅助推理的方法，该方法利用视觉基础模型逐步将复杂场景分解为与任务相关的场景图，从而增强VLMs的空间逻辑推理能力，优于所有先前的方法。代码和数据集可在https://github.com/xieyc99/SpatiaLQA上获得。

英文摘要：

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual question answering and logical reasoning, they still lack the ability to make reasonable decisions in complex real-world environments. We define this ability as spatial logical reasoning, which not only requires understanding the spatial relationships among objects in complex scenes, but also the logical dependencies between steps in multi-step tasks. To bridge this gap, we introduce Spatial Logical Question Answering (SpatiaLQA), a benchmark designed to evaluate the spatial logical reasoning capabilities of VLMs. SpatiaLQA consists of 9,605 question answer pairs derived from 241 real-world indoor scenes. We conduct extensive experiments on 41 mainstream VLMs, and the results show that even the most advanced models still struggle with spatial logical reasoning. To address this issue, we propose a method called recursive scene graph assisted reasoning, which leverages visual foundation models to progressively decompose complex scenes into task-relevant scene graphs, thereby enhancing the spatial logical reasoning ability of VLMs, outperforming all previous methods. Code and dataset are available at https://github.com/xieyc99/SpatiaLQA.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。