发表机构
University of California, Los Angeles; University of California, Merced（加州大学洛杉矶分校; 加州大学默塞德分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CoRF提出跨场景射频合成方法，通过分离场景传播与阵列物理，实现无需场景特定训练即可从稀疏测量合成空间频谱，在35个模拟场景中显著优于基线。
AI 中文摘要
现有的射频（RF）神经场分别拟合每个场景，使得新场景部署需要大量测量和优化。本研究探讨了摊销式跨场景空间频谱合成，其中共享模型学习跨场景的传播，并从稀疏的目标场景测量中实例化未见过的场景，无需针对特定场景进行训练。为实现这一目标，CoRF将学习到的场景相关传播与已知的接收器阵列观测模型分离。一组无序的仅频谱参考条件化一个规范锚定场，为每个查询生成到达方向和查询相关的分量功率。解析阵列物理将这些分量映射到接收器协方差，再映射到空间频谱。这种分解保持预训练的传播模型冻结，使得在单次参考条件化传递后能够在任意查询位置进行合成。一个必要的局部参考容量界和误差分解进一步表征了该公式。在涵盖七个类别的35个模拟场景中，CoRF在未见过的代表场景类别变体上比最强基线高出7.09 dB PSNR，在完全未见过的场景类别上高出6.97 dB。
英文摘要
Existing radio-frequency (RF) neural fields fit each scene separately, making new-scene deployment measurement- and optimization-intensive. This work studies amortized cross-scene spatial spectrum synthesis, where a shared model learns propagation across scenes and instantiates an unseen scene from sparse target-scene measurements without scene-specific training. To achieve this, CoRF separates learned scene-dependent propagation from the known receiver-array observation model. An unordered set of spectrum-only references conditions a canonical anchor field, producing arrival directions and query-dependent component powers for each query. Analytic array physics maps these components to the receiver covariance and then to the spatial spectrum. This factorization keeps the pretrained propagation model frozen, enabling synthesis at arbitrary query locations after a single reference-conditioning pass. A necessary local reference-capacity bound and an error decomposition further characterize the formulation. Across 35 simulated scenes spanning seven categories, CoRF outperforms the strongest baseline by 7.09 dB PSNR on unseen variants of represented scene categories and by 6.97 dB on entirely unseen scene categories.
