Reasoning with Pixel-level Precision: QVLM Architecture and SQuID Dataset for Quantitative Geospatial Analytics
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Spatial ReasoningSimilar Papers 제목 키워드 기반
SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for …
3D Semantic SegmentationVisual GroundingMedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
Accurately grounding regions of interest (ROIs) is critical for diagnosis and treatment planning in medical imaging. While multimodal large language models (MLLMs) combine visual perception with natural language, current…
Reinforcement LearningSPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temp…
Visual GroundingBeyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos
State-of-the-art spatio-temporal action detection (STAD) methods show promising results for extracting soccer events from broadcast videos. However, when operated in the high-recall, low-precision regime required for exh…
Action DetectionDecoderDenoisingEvent ExtractionI2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing
Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tas…
Spatial ReasoningImage Editing