发表机构
Monash University; The Chinese University of Hong Kong（莫纳什大学; 香港中文大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有多视图空间推理方法的跨视图对齐脆弱等问题，提出无需微调的模型无关框架Vantage，结合VLM与3D基础模型，经实验在五个基准上提升了多视图空间理解性能。
AI 中文摘要
现有的多视图空间推理方法大多基于稀疏输入视图运行，因此视觉语言模型（VLMs）被限制在这些固定视图内理解场景并推断空间关系，导致跨视图对齐脆弱以及几何到语言的瓶颈。为解决这些问题，我们提出了一种新颖的搜索-视图推理方法，通过定位与问题相关的视图来寻找隐式跨视图空间证据，以支持空间推理。为实现该方法，我们提出了Vantage，这是一种无需微调、与模型无关的推理框架，它将VLM与3D基础模型配对：首先是基于视点的推理阶段，用于问题分析和视图规划；随后是基于几何的证据增强阶段，以有效合成视觉证据并将其融入最终推理。在六个VLMs上进行的综合实验表明，该方法在五个基准上取得了一致的改进，且无需微调。总体而言，通过基于视图的推理揭示空间证据，Vantage可大幅减少对基于语言的跨视图对齐的依赖，提升多视图空间理解能力。我们的代码可在该https URL获取。
英文摘要
Existing approaches to multi-view spatial reasoning operate largely on sparse input views. Vision-language models (VLMs) are thus restricted to understand a scene and infer spatial relations within these fixed views, leading to fragile cross-view alignment and geometry-to-language bottleneck. To address these issues, we formulate a novel Seek-and-View reasoning approach to find implicit cross-view spatial evidence by locating a question-relevant view to support the spatial reasoning. To realize this approach, we propose Vantage, a training-free model-agnostic reasoning framework that pairs a VLM with a 3D foundation model: a viewpoint-grounded reasoning stage for question analysis and view planning, followed by a geometry-grounded evidence augmentation stage to effectively synthesize and incorporate visual evidence into the final reasoning. Comprehensive experiments on six VLMs demonstrate consistent improvements on five benchmarks without fine-tuning. Overall, by revealing spatial evidence through view-grounded reasoning, Vantage can largely reduce reliance on language-based cross-view alignment and improve multi-view spatial understanding. Our code is available at https://github.com/q1xiangchen/Vantage.
CommentsProject page: https://seekandview2026.github.io; Code: https://github.com/q1xiangchen/Vantage
