Abstract:Vision-Language Models (VLMs) exhibit emerging spatial reasoning capabilities, yet they remain unreliable on tasks requiring precise spatial understanding, such as viewpoint reasoning, directional comparison, and distance estimation. In multi-view images and monocular videos, relevant spatial cues are often sparse and distributed across redundant observations, making them difficult to organize and exploit. Reconstruction-based Vision Foundation Models (VFMs) offer a natural way to aggregate such observations into explicit spatial memory, such as point clouds. However, simply exposing reconstruction models as free-form tools is brittle, VLMs may invoke tools incorrectly, skip required spatial transformations, or misuse intermediate results. We propose \textbf{Reasmory}, a framework that formulates spatial reasoning as structured program execution over reconstructed spatial memory. Reasmory constructs explicit 3D memory, augments it with semantically grounded 3D object instances, and introduces a lightweight Domain-Specific Language (DSL) that constrains how VLMs query objects and cameras, transform viewpoints, and render observations during reasoning. Generated programs are parsed and validated before execution, enabling more reliable interaction with spatial memory than unconstrained tool use. Experiments on multi-view image and video spatial reasoning benchmarks show consistent gains of 6--18\% over strong baselines, including GPT-5-mini and Gemini-3-flash, indicating that explicit 3D memory is most useful when accessed through constrained, validated operations rather than free-form tool calls.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.00963 [cs.CV] |
| (or arXiv:2606.00963v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.00963 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jixuan He [view email]
[v1]
Sun, 31 May 2026 02:36:57 UTC (4,125 KB)