SyncAI.news, a Varaisys broadcasting
Geometric Encoding for Spatial Reasoning in Vision-Language Models
AJ

Antonio Jun, Haoshui Yu, Zhengyi Lu, Huirong Fu, Yao Qiang

· 1 min read

ResearcharXiv cs.CV

Geometric Encoding for Spatial Reasoning in Vision-Language Models

arXiv:2609.34148v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are far more reliable at recognizing what appears in a video than at reasoning about its spatial and temporal properties, such as metric distances, object dimensions, and consistent object identities across frames. We present Geometric Code, a perception-to-geometry pipeline that computes explicit spatial structure from video and supplies it to VLMs as context to augment reasoning. A perception layer segments and classifies objects and recovers depth, camera pose, and intrinsics from monocular RGB video. A deterministic geometric engine then back-projects, merges, and cleans these outputs into a spatial code, including per-object positions, dimensions, counts, inter-object distances, appearance order, and room geometry. The code is serialized into VLMs' prompts, either alongside the video or replacing it entirely. Specifically, there is no component trained or fine-tuned in our approach. On VSI-Bench, augmenting 2B and 4B open models with the spatial code improves average accuracy by +4.1 points over the frames-only baseline, with the largest gains on numeric estimation tasks such as absolute distance (+24.1 points). The results suggest that explicitly computed geometry, delivered through the language channel, recovers spatial competence that small VLMs cannot extract from pixels alone.

Original source

This story was published by arXiv cs.CV and written by Antonio Jun, Haoshui Yu, Zhengyi Lu, Huirong Fu, Yao Qiang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News