RMPrior: 融合传播先验与扩散精炼的高效无线电地图构建
RMPrior: Bridging Propagation Priors and Diffusion Refinement for Efficient Radio Map Construction
AI总结:
提出一种中起点采样策略,通过将传播先验扰动至中间扩散时间步,仅执行剩余反向步骤,在加速2.01倍的同时提升重建质量,并理论分析了初始化差距的上界及截断条件。
摘要:
扩散模型通过迭代去噪实现高保真无线电地图构建,但其采样成本限制了在需要反复更新无线电地图的动态无线系统中的实用性。同时,经典传播模型编码了有价值的场景级知识,而标准扩散推理通过从纯高斯噪声初始化完全丢弃了这些知识。本文通过中起点采样策略桥接了传播先验与扩散精炼。匹配的传播先验被扰动至中间扩散时间步,预训练的扩散骨干仅执行剩余的反向步骤,将计算集中在多径感知精炼上,而非从噪声完全重建。我们提供了理论分析,建立了初始化差距的上界、截断提高重建保真度的充分条件,以及在激进截断下先验质量敏感性的形式化刻画。在IRT4HighRes上的实验表明,在$P_{ ext{start}}=0.5$时,所提方法实现了2.01倍的加速,同时在NMSE、RMSE、SSIM和PSNR上均优于全步基线。跨三个不同保真度传播模型的先验质量消融实验证实,重建质量跟踪先验质量,且敏感性在更短的反向轨迹下放大,与理论预测一致。这些结果还表明,中起点重建质量可作为不同传播模型场景级保真度排序的代理指标。
英文摘要:
Diffusion models achieve high-fidelity radio map construction through iterative denoising, yet their sampling cost limits practicality in dynamic wireless systems where radio maps must be refreshed repeatedly. Meanwhile, classical propagation models encode valuable scene-level knowledge that standard diffusion inference discards entirely by initializing from pure Gaussian noise. This paper bridges propagation priors and diffusion refinement through a mid-start sampling strategy. A matched propagation prior is perturbed to an intermediate diffusion timestep, and the pretrained diffusion backbone executes only the remaining reverse steps, focusing computation on multipath-aware refinement rather than full reconstruction from noise. We provide theoretical analysis establishing an upper bound on the initialization gap, a sufficient condition under which truncation improves reconstruction fidelity, and a formal characterization of prior-quality sensitivity under aggressive truncation. Experiments on IRT4HighRes show that, at $P_{\text{start}}=0.5$, the proposed method achieves a $2.01\times$ speedup while simultaneously improving NMSE, RMSE, SSIM, and PSNR over the full-step baseline. A prior-quality ablation across three propagation models of different fidelity confirms that reconstruction quality tracks prior quality, with the sensitivity amplified under shorter reverse trajectories, consistent with the theoretical predictions. These results also suggest that mid-start reconstruction quality can serve as a proxy for ranking the scene-level fidelity of different propagation models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。