Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery?

arXiv:2609.17882 · cs.CV, cs.CY, cs.LG · Submitted 2026-09-15 · Read on arXiv

cs.CV, cs.CY, cs.LG

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: 29 pages, 4 figures, 9 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 88× in this paper · explained in 7 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Conformal Prediction — 15× in this paper · explained in 5 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Consistency — 11× in this paper · explained in 3 episodes
• Vision-Language Model — 10× in this paper
• Degeneracy — 8× in this paper · explained in 3 episodes
• Empirical Coverage — 7× in this paper · explained in 2 episodes
• Exchangeability — 6× in this paper · explained in 2 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Foundation Models — 5× in this paper · explained in 7 episodes
• Self-consistency — 5× in this paper · explained in 2 episodes
• Uncertainty Quantification — 5× in this paper · explained in 8 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 3× in this paper · explained in 6 episodes
• Abstention — 2× in this paper · explained in 1 episode
• Americans with Disabilities Act — 2× in this paper
• Fidelity — 2× in this paper · explained in 2 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Semantic Similarity — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Domain Shift — 1× in this paper · explained in 4 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Personal Information Protection Act — 1× in this paper
• Transferability — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View
• Towards Human-AI Accessibility Mapping in India: VLM-Guided Annotations and POI-Centric Analysis in Chandigarh
• VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation
• UrbanVGGT: Scalable Sidewalk Width Estimation from Street View Images
• Non-Determinism of "Deterministic" LLM Settings
• Uncertainty-Aware Evaluation for Vision-Language Models
• Language Models with Conformal Factuality Guarantees
• Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction
• CONRep: Uncertainty-Aware Vision-Language Report Drafting Using Conformal Prediction
• Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models
• Conformal Sets in Multiple-Choice Question Answering under Black-Box Settings with Provable Coverage Guarantees
• Empirical Bayes Conformal Prediction for Vision and Language Models
• LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
• Qwen3-VL Technical Report
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• OASIS: Automated Assessment of Urban Pedestrian Paths at Scale

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models