RoadFusion: Latent Diffusion Model for Pavement Defect Detection

TL;DR

RoadFusion introduces a novel latent diffusion-based framework for pavement defect detection, effectively generating synthetic defects and adapting features to overcome data scarcity, domain shift, and variability challenges, achieving state-of-the-art results.

Contribution

The paper presents a new framework combining synthetic defect generation with dual-path feature adaptation for improved pavement defect detection.

Findings

Achieves state-of-the-art performance on six benchmark datasets.

Effectively handles data scarcity and domain shift issues.

Improves defect classification and localization accuracy.

Abstract

Pavement defect detection faces critical challenges including limited annotated data, domain shift between training and deployment environments, and high variability in defect appearances across different road conditions. We propose RoadFusion, a framework that addresses these limitations through synthetic anomaly generation with dual-path feature adaptation. A latent diffusion model synthesizes diverse, realistic defects using text prompts and spatial masks, enabling effective training under data scarcity. Two separate feature adaptors specialize representations for normal and anomalous inputs, improving robustness to domain shift and defect variability. A lightweight discriminator learns to distinguish fine-grained defect patterns at the patch level. Evaluated on six benchmark datasets, RoadFusion achieves consistently strong performance across both classification and localization tasks, setting new state-of-the-art in multiple metrics relevant to real-world road inspection.