SpatiaLQA：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
可复用其递归场景图辅助推理框架：用视觉基础模型把复杂室内场景逐步分解为与任务相关的场景图，再交给 VLM 做多步空间逻辑推理，这一思路可直接迁移到具身导航、机器人操作等需要空间关系判断的视觉任务。
原文依据 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
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉语言模型（VLM）凭借出色的理解与推理能力，正日益应用于真实场景。尽管 VLM 在常规视觉问答与逻辑推理中已展现出令人印象深刻的能力，但它们在复杂真实环境中仍缺乏做出合理决策的能力。我们将这一能力定义为空间逻辑推理，它不仅要求理解复杂场景中物体之间的空间关系，还要求理解多步任务中各步骤之间的逻辑依赖关系。为弥补这一空白，我们提出空间逻辑问答（SpatiaLQA），一个用于评估 VLM 空间逻辑推理能力的基准。SpatiaLQA 包含 9,605 个问答对，源自 241 个真实室内场景。我们在 41 个主流 VLM 上开展了大量实验，结果表明即使是最先进的模型在空间逻辑推理上仍存在困难。为解决该问题，我们提出一种名为递归场景图辅助推理的方法，它利用视觉基础模型将复杂场景逐步分解为与任务相关的场景图，从而增强 VLM 的空间逻辑推理能力，并优于此前所有方法。我们将很快发布代码与数据集。
英文原文摘要 1356 字符
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. We will release our code and dataset soon.