This study proposes C2B-DeformYOLO，an end-to-end real-time unmanned aerial vehicle(UAV)road damage detector built on YOLOv10，with targeted architectural improvements to address two core issues:cross-scale discontinuous representations of elongated cracks and accurate localization of nonconvex pothole boundaries. First，a Continuous Conditioned Gather Distribute neck (C2GD Neck)is introduced，which performs global information gathering over multi-level features and generates continuous conditioning weights to adaptively allocate and fuse features in a bidirectional manner. This design strengthens coherent responses for thin crack patterns and enhances long-range dependency modeling across scales. Second，Budgeted Offset Sparse Convolution(BOS Conv)is presented，which conducts sparse offset sampling and reconstruction on high-response regions under a constrained computation budget，improving geometric alignment and boundary deformation modeling while preserving efficient inference. Experiments on a UAV road damage dataset and the public RDD2022 benchmark demonstrated consistent gains in detection accuracy and cross-domain generalization over the baseline，without sacrificing real-time performance.