arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.02790cs.LGeess.SP
收藏

RadioDiff-Flux:通过生成式去噪扩散模型轨迹中点重用高效构建无线电地图

RadioDiff-Flux: Efficient Radio Map Construction via Generative Denoise Diffusion Model Trajectory Midpoint Reuse

State Key Laboratory of ISN and School of Telecommunications Engineering, Xidian University(信息与通信工程国家重点实验室和西安电子科技大学电信工程学院);Department of Electrical and Computer Engineering, University of Waterloo(滑铁卢大学电气与计算机工程系)

Xiucheng Wang, Peilin Zheng, Honggang Jia, Nan Cheng, Ruijin Sun, Conghao Zhou, Xuemin Shen

AI总结:

RadioDiff-Flux通过生成式去噪扩散模型轨迹中点重用,高效构建无线电地图,实现快速且高保真的RM生成。

摘要:

准确的无线电地图(RM)构建对于实现环境感知和自适应无线通信至关重要。然而,在未来6G场景中,高速网络实体和快速变化的环境使得满足实时需求变得非常具有挑战性。尽管生成扩散模型(DMs)可以利用第二级延迟实现最先进的准确性,但其迭代性质导致在敏感延迟场景中推断延迟过高。在本文中,通过揭示扩散过程的一个关键结构性质:在语义相似的场景中,潜在的中点保持高度一致,我们提出了RadioDiff-Flux,一种新的两阶段潜在扩散框架,将静态环境建模与动态细化解耦,使预计算的中点可以被重用以避免冗余去噪。特别是,第一阶段仅使用静态场景特征生成粗略的潜在表示,该表示可以在相似场景中缓存和共享。第二阶段利用预训练模型适应此表示以适应动态条件和发射机位置,从而避免重复的早期阶段计算。所提出的RadioDiff-Flux在保持保真度的同时显著减少了推断时间。实验结果表明,RadioDiff-Flux可以实现高达50倍的加速,同时仅损失不到0.15%的准确性,证明了其在6G网络中快速、可扩展的RM生成中的实际用途。

英文摘要:

Accurate radio map (RM) construction is essential to enabling environment-aware and adaptive wireless communication. However, in future 6G scenarios characterized by high-speed network entities and fast-changing environments, it is very challenging to meet real-time requirements. Although generative diffusion models (DMs) can achieve state-of-the-art accuracy with second-level delay, their iterative nature leads to prohibitive inference latency in delay-sensitive scenarios. In this paper, by uncovering a key structural property of diffusion processes: the latent midpoints remain highly consistent across semantically similar scenes, we propose RadioDiff-Flux, a novel two-stage latent diffusion framework that decouples static environmental modeling from dynamic refinement, enabling the reuse of precomputed midpoints to bypass redundant denoising. In particular, the first stage generates a coarse latent representation using only static scene features, which can be cached and shared across similar scenarios. The second stage adapts this representation to dynamic conditions and transmitter locations using a pre-trained model, thereby avoiding repeated early-stage computation. The proposed RadioDiff-Flux significantly reduces inference time while preserving fidelity. Experiment results show that RadioDiff-Flux can achieve up to 50 acceleration with less than 0.15% accuracy loss, demonstrating its practical utility for fast, scalable RM generation in future 6G networks.

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。

↑