面向空间频谱合成的可泛化射频辐射场
Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis
把 NeRF 式的辐射场从光学域搬到射频域，并用几何感知 Transformer 编码器实现跨场景泛化，为视觉研究者提供「场景无关潜变量辐射场 + 神经光线追踪」这一可迁移范式，可用于无线感知、波束预测与跨场景泛化建模。
原文依据 a geometry-aware Transformer encoder that captures spatial correlations from neighboring transmitters to learn a scene-independent latent RF radiance field
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 GRaF，即可泛化射频（RF）辐射场，这是一个对射频信号传播进行建模、从而在任意发射机或接收机位置合成空间频谱的框架，其中每个频谱度量接收机处所有周围方向上的信号功率。与将原始神经辐射场（NeRF）适配到射频域并做场景特定训练的最优方法不同，GRaF 能够跨场景泛化地合成频谱。为实现这一点，我们证明了射频域中的一种插值理论：来自某个发射机的空间频谱可以利用地理上邻近的发射机的频谱来近似。基于该理论，GRaF 包含两个部分：(i) 一个几何感知 Transformer 编码器，它从邻近发射机捕获空间相关性，以学习与场景无关的潜变量射频辐射场；(ii) 一种神经光线追踪算法，用于估计接收机处的频谱接收。实验结果表明，GRaF 在单场景基准上优于现有方法，并在未见过的场景布局上达到最优性能。
英文原文摘要 1126 字符
We present GRaF, Generalizable Radio-Frequency (RF) Radiance Fields, a framework that models RF signal propagation to synthesize spatial spectra at arbitrary transmitter or receiver locations, where each spectrum measures signal power across all surrounding directions at the receiver. Unlike state-of-the-art methods that adapt vanilla Neural Radiance Fields (NeRF) to the RF domain with scene-specific training, GRaF generalizes across scenes to synthesize spectra. To enable this, we prove an interpolation theory in the RF domain: the spatial spectrum from a transmitter can be approximated using spectra from geographically proximate transmitters. Building on this theory, GRaF comprises two components: (i) a geometry-aware Transformer encoder that captures spatial correlations from neighboring transmitters to learn a scene-independent latent RF radiance field, and (ii) a neural ray tracing algorithm that estimates spectrum reception at the receiver. Experimental results demonstrate that GRaF outperforms existing methods on single-scene benchmarks and achieves state-of-the-art performance on unseen scene layouts.