# PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis

Source: [PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis](<https://www.sota2.com/research/paper/69d33ddc7d0172140ec7350e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-07T05:00:04.607Z

Authors: Dexiang Li, Zhenning Che, Haijun Zhang, Dongliang Zhou, Zhao Zhang, Yahong Han

Published: 2026-04-03T07:15:41.000Z

## Abstract

Pavement condition assessment is essential for road safety and maintenance. Existing research has made significant progress. However, most studies focus on conventional computer vision tasks such as classification, detection, and segmentation. In real-world applications, pavement inspection requires more than visual recognition. It also requires quantitative analysis, explanation, and interactive decision support. Current datasets are limited. They focus on unimodal perception. They lack support for multi-turn interaction and fact-grounded reasoning. They also do not connect perception with vision-language analysis. To address these limitations, we introduce PaveBench, a large-scale benchmark for pavement distress perception and interactive vision-language analysis on real-world highway inspection images. PaveBench supports four core tasks: classification, object detection, semantic segmentation, and vision-language question answering. It provides unified task definitions and evaluation protocols. On the visual side, PaveBench provides large-scale annotations and includes a curated hard-distractor subset for robustness evaluation. It contains a large collection of real-world pavement images. On the multimodal side, we introduce PaveVQA, a real-image question answering (QA) dataset that supports single-turn, multi-turn, and expert-corrected interactions. It covers recognition, localization, quantitative estimation, and maintenance reasoning. We evaluate several state-of-the-art methods and provide a detailed analysis. We also present a simple and effective agent-augmented visual question answering framework that integrates domain-specific models as tools alongside vision-language models. The dataset is available at: https://huggingface.co/datasets/MML-Group/PaveBench.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on PaveBench](<https://www.sota2.com/research/sota/image-classification-on-pavebench.md>): Image Classification; PaveBench; Accuracy: not recorded.

- [Object Detection on PaveBench](<https://www.sota2.com/research/sota/object-detection-on-pavebench.md>): Object Detection; PaveBench; mAP: not recorded.

- [Semantic Segmentation on PaveBench](<https://www.sota2.com/research/sota/semantic-segmentation-on-pavebench.md>): Semantic segmentation; PaveBench; mPrec: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.02804>)

[PDF](<https://arxiv.org/pdf/2604.02804.pdf>)