MMPerspective: 多模态大语言模型是否理解视角？一个全面的视角感知、推理和鲁棒性评估基准
MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
AI总结：
MMPerspective通过10个任务评估多模态大语言模型在视角感知、推理和鲁棒性方面的能力，揭示其在空间一致性维持和组合推理上的局限性。
摘要：
理解视角是人类视觉感知的基础，但多模态大语言模型（MLLMs）内部化视角几何的程度仍不明确。我们引入MMPerspective，第一个专门设计用于系统评估MLLMs视角理解的基准，通过10个精心设计的任务在三个互补的维度上：视角感知、推理和鲁棒性。我们的基准包含2711个现实世界和合成图像实例，以及5083个问题-答案对，探测关键能力，如消失点感知和计数、视角类型推理、三维空间中线关系理解、对视角保持变换的不变性等。通过全面评估43种最先进的MLLMs，我们发现显著的局限性：虽然模型在表层感知任务上表现出色，但在组合推理和在扰动下维持空间一致性方面却存在困难。我们的分析进一步揭示了模型架构、规模和视角能力之间的有趣模式，突显了鲁棒性瓶颈和链式思考提示的好处。MMPerspective为诊断和推进视觉-语言系统中的空间理解建立了有价值的测试平台。资源可访问：https://yunlong10.github.io/MMPerspective/
英文摘要：
Understanding perspective is fundamental to human visual perception, yet the extent to which multimodal large language models (MLLMs) internalize perspective geometry remains unclear. We introduce MMPerspective, the first benchmark specifically designed to systematically evaluate MLLMs' understanding of perspective through 10 carefully crafted tasks across three complementary dimensions: Perspective Perception, Reasoning, and Robustness. Our benchmark comprises 2,711 real-world and synthetic image instances with 5,083 question-answer pairs that probe key capabilities, such as vanishing point perception and counting, perspective type reasoning, line relationship understanding in 3D space, invariance to perspective-preserving transformations, etc. Through a comprehensive evaluation of 43 state-of-the-art MLLMs, we uncover significant limitations: while models demonstrate competence on surface-level perceptual tasks, they struggle with compositional reasoning and maintaining spatial consistency under perturbations. Our analysis further reveals intriguing patterns between model architecture, scale, and perspective capabilities, highlighting both robustness bottlenecks and the benefits of chain-of-thought prompting. MMPerspective establishes a valuable testbed for diagnosing and advancing spatial understanding in vision-language systems. Resources available at: https://yunlong10.github.io/MMPerspective/
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。
