Depth estimation remains central to autonomous driving, and radar-camera fusion offers robustness in adverse conditions by providing complementary geometric cues. In this paper, we present XD-RCDepth, a lightweight architecture that reduces the parameters by 29.7% relative to the state-of-the-art lightweight baseline while maintaining comparable accuracy. To preserve performance under compression and enhance interpretability, we introduce two knowledge-distillation strategies: an explainability-aligned distillation that transfers the teacher's saliency structure to the student, and a depth-distribution distillation that recasts depth regression as soft classification over discretized bins. Together, these components reduce the MAE compared with direct training with 7.97% and deliver competitive accuracy with real-time efficiency on nuScenes and ZJU-4DRadarCam datasets.
@article{arxiv.2510.13565,
title = {XD-RCDepth: Lightweight Radar-Camera Depth Estimation with Explainability-Aligned and Distribution-Aware Distillation},
author = {Huawei Sun and Zixu Wang and Xiangyuan Peng and Julius Ott and Georg Stettinger and Lorenzo Servadei and Robert Wille},
journal= {arXiv preprint arXiv:2510.13565},
year = {2025}
}