Current intelligent inspection methods often lack robustness when identifying urban road defects under poor lighting and blurry conditions. Based on the CRDDC2022_Japan dataset, this study introduces an integrated road-distress detection framework that combines Retinex-S image enhancement with an improved YOLOv8 detector. The enhancement stage performs white balance correction, gamma preprocessing, RGB-to-HSI conversion, SelfDeblur-based restoration on the Intensity channel, wavelet-based Retinex enhancement with MSE-guided reflectance refinement, adaptive saturation adjustment, and HSI-to-RGB reconstruction to recover visibility while preserving details. The detection stage replaces the original YOLOv8s backbone with MobileNetV3, reconstructs the neck with GSConv and CSPHet, and redesigns the head with RepConv while adding a small-object detection branch. On the CRDDC2022_Japan dataset, the proposed method improves mAP@0.5 from 0.643 to 0.692 and reduces the parameter count from 11.1M to 9.3M compared with YOLOv8s while also lowering GFLOPS from 28.8 to 15.7. These results indicate that the proposed framework offers an effective accuracy–efficiency trade-off for road-distress detection under low-illumination and blurred conditions.