Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reasoning with Pixel-level Precision: QVLM Architecture and SQuID Dataset for Quantitative Geospatial Analytics

Peter A. Massih, Eric Cosatto

TL;DR

This work proposes QVLM (Quantitative Vision-Language Model), a code-generation architecture that maintains pixel precision by decoupling language understanding from visual analysis, and reveals that, for quantitative spatial reasoning, architectural decoupling enables better accuracy on quantitative tasks.

Abstract

Current Vision-Language Models (VLMs) fail at quantitative spatial reasoning because their architectures destroy pixel-level information required for counting and measurements. Vision encoders compress images through patch embeddings, reducing spatial indexing and losing the precise pixel-level tracking required for accurate counting. We present two contributions to address this fundamental limitation. First, we introduce SQuID (Satellite Quantitative Intelligence Dataset), a benchmark of 2,000 satellite image Question-Answer pairs with both numerical range and categorical answers, designed to evaluate quantitative spatial reasoning. The dataset spans three difficulty tiers with annotations automatically generated from human labels and their learned variability. Second, we propose QVLM (Quantitative Vision-Language Model), a code-generation architecture that maintains pixel precision by decoupling language understanding from visual analysis. Instead of encoding images into embeddings, QVLM generates executable code that first calls a segmentation model to obtain pixel-level masks, then operates directly on these masks, preserving spatial indexing throughout the reasoning process. Our experiments show that QVLM using GPT-5 as coder achieves 42.0% accuracy on SQuID compared to 28.1% for a VLM prompted with image-question pairs. Our work reveals that, for quantitative spatial reasoning, architectural decoupling enables better accuracy on quantitative tasks.

Reasoning with Pixel-level Precision: QVLM Architecture and SQuID Dataset for Quantitative Geospatial Analytics

TL;DR

This work proposes QVLM (Quantitative Vision-Language Model), a code-generation architecture that maintains pixel precision by decoupling language understanding from visual analysis, and reveals that, for quantitative spatial reasoning, architectural decoupling enables better accuracy on quantitative tasks.

Abstract

Current Vision-Language Models (VLMs) fail at quantitative spatial reasoning because their architectures destroy pixel-level information required for counting and measurements. Vision encoders compress images through patch embeddings, reducing spatial indexing and losing the precise pixel-level tracking required for accurate counting. We present two contributions to address this fundamental limitation. First, we introduce SQuID (Satellite Quantitative Intelligence Dataset), a benchmark of 2,000 satellite image Question-Answer pairs with both numerical range and categorical answers, designed to evaluate quantitative spatial reasoning. The dataset spans three difficulty tiers with annotations automatically generated from human labels and their learned variability. Second, we propose QVLM (Quantitative Vision-Language Model), a code-generation architecture that maintains pixel precision by decoupling language understanding from visual analysis. Instead of encoding images into embeddings, QVLM generates executable code that first calls a segmentation model to obtain pixel-level masks, then operates directly on these masks, preserving spatial indexing throughout the reasoning process. Our experiments show that QVLM using GPT-5 as coder achieves 42.0% accuracy on SQuID compared to 28.1% for a VLM prompted with image-question pairs. Our work reveals that, for quantitative spatial reasoning, architectural decoupling enables better accuracy on quantitative tasks.
Paper Structure (22 sections, 2 equations, 11 figures, 11 tables)

This paper contains 22 sections, 2 equations, 11 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Quantitative Limitations of VLMs
  4. Code Generation for Visual Reasoning
  5. Segmentation for Quantitative Precision
  6. Positioning SQuID
  7. The SQuID Dataset
  8. Dataset Construction
  9. Question Types and Difficulty Tiers
  10. Human-Validated Acceptable Ranges
  11. Quality Assurance
  12. QVLM
  13. Model Architecture
  14. Code Generation and Spatial Analysis API
  15. Segmentation Models
  16. ...and 7 more sections

Figures (11)

  • Figure 1: Grid-based annotation interface built on Turkle with adjustable resolution (10×10 to 320×320). (a) Annotators select grid cells covering target land-cover classes to answer percentage questions. (b) Distance ruler tool enables precise measurements for proximity-based questions.
  • Figure 2: SQuID examples across difficulty tiers. (a) Basic quantification: single-step percentage calculation. (b) Spatial relationships: counting with size filtering. (c) Complex multi-condition: size filtering + distance transform + intersection (GSD: 0.3m for all). Note: Questions shown here are abbreviated for layout.
  • Figure 3: SQuID dataset composition.(A) Three difficulty tiers. (B) Four data sources at 0.3m--1.0m GSD. (C) Top 5 question categories and percentage contribution of all others question types
  • Figure 4: QVLM vs Traditional VLM Architecture. Top: QVLM decouples language understanding from visual analysis. An LLM generates executable code that orchestrates segmentation models, operating directly on pixel-accurate masks. Bottom: Traditional VLMs compress images via patch embedding (256× fold), destroying the spatial indexing required for quantitative reasoning.
  • Figure 5: Semantic and instance segmentation example. Left: input RGB satellite imagery. Right: Segmentation output - urban (grey), forest (dark green), agricultural/grassy (light green), barren (orange), water (blue), solar panels (dark blue), buildings (magenta).
  • ...and 6 more figures