迷失在空间中？视觉-语言模型在相对相机姿态估计中挣扎
Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
AI总结：
研究视觉-语言模型在相对相机姿态估计中的表现，发现其在多视角空间推理中存在显著不足，尽管人类和专用几何方法表现良好，但VLMs仍处于初级水平，揭示了跨视角对应和投影相机运动理解等关键能力缺失。
摘要：
我们研究了视觉-语言模型（VLMs）能否通过图像对解决相对相机姿态估计（RCPE），这是多视角空间推理的直接测试。我们将RCPE视为一个离散的言语分类任务，并引入了VRRPI-Bench（基于真实RGB-D帧和以物体为中心的相机运动）和VRRPI-Diag（隔离单个运动自由度）。人类（0.91）和专用几何管道如LoFTR（0.99）能够可靠地解决该任务，但最好的VLM仅达到0.66，大多数其他模型仍接近随机。我们的分析表明，这一差距并非基本的空间能力：强大的VLM在单图像基准上接近天花板，但一旦推理必须跨视角进行，大多数仍接近随机。它们在源-目标反转下不稳定（最佳一致性为59.7%），即使在简化单自由度设置中也表现薄弱，尤其是在光轴运动如翻滚和深度平移（GPT-5：翻滚0.46）上。这些失败是有用的：它们定位了具体缺失的能力，即跨视角对应、视图一致推理和投影相机运动理解，使RCPE成为改进VLMs多视角空间推理的针对性诊断。
英文摘要：
We study whether vision-language models (VLMs) can solve relative camera pose estimation (RCPE) from image pairs, a direct test of multi-view spatial reasoning. We cast RCPE as a discrete verbal classification task and introduce \texttt{VRRPI-Bench}, built from real RGB-D frames with object-centric camera motion, and \texttt{VRRPI-Diag}, which isolates individual motion degrees of freedom. Humans (0.91) and specialized geometric pipelines such as LoFTR (0.99) solve the task reliably, yet the best VLM reaches only 0.66 and most others remain near random. Our analyses show that this gap is not basic spatial competence: strong VLMs are near ceiling on single-image benchmarks, but most remain near random once reasoning must span views. They are unstable under source-target reversal (best 59.7\% consistency) and remain weak even in simplified single-DoF settings, especially on optical-axis motions such as roll and depth translation (GPT-5: 0.46 on roll). These failures are useful: they localize concrete missing capabilities, namely cross-view correspondence, view-consistent reasoning, and projective camera-motion understanding, making RCPE a targeted diagnostic for improving multi-view spatial reasoning in VLMs.
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。
