Deterministic channel modeling maps a physical environment to its site-specific electromagnetic response. Ray tracing produces complete multi-dimensional channel information but remains prohibitively expensive for area-wide deployment. We identify line-of-sight (LoS) region determination as the dominant bottleneck. To address this, we propose D$^2$LoS, a physics-informed neural network that reformulates dense pixel-level LoS prediction into sparse vertex-level visibility classification and projection point regression, avoiding the spectral bias at sharp boundaries. A geometric post-processing step enforces hard physical constraints, yielding exact piecewise-linear boundaries. Because LoS computation depends only on building geometry, cross-band channel information is obtained by updating material parameters without retraining. We also construct RayVerse-100, a ray-level dataset spanning 100 urban scenarios with per-ray complex gain, angle, delay, and geometric trajectory. Evaluated against rigorous ray tracing ground truth, D$^2$LoS achieves 3.28~dB mean absolute error in received power, 4.65$^\circ$ angular spread error, and 20.64~ns delay spread error, while accelerating visibility computation by over 25$\times$.

翻译：确定性信道建模将物理环境映射为其特定位置上的电磁响应。射线追踪能生成完整的多维信道信息，但因其计算成本过高而难以实现大范围部署。我们发现视线区域判定是主要瓶颈。为此，我们提出D$^2$LoS——一种基于物理信息的神经网络，将稠密的像素级视线预测重构为稀疏的顶点级可见性分类与投影点回归，从而避免了尖锐边界处的谱偏置。几何后处理步骤强制执行硬物理约束，生成精确的分段线性边界。由于视线计算仅依赖于建筑物几何结构，跨频段信道信息可通过更新材料参数获得而无需重新训练。我们还构建了RayVerse-100数据集——包含100个城市场景的射线级数据集，每条射线均包含复增益、角度、时延和几何轨迹。以严格的射线追踪真值为基准，D$^2$LoS在接收功率上达到3.28dB的平均绝对误差，角扩展误差为4.65$^\circ$，时延扩展误差为20.64ns，同时将可见性计算加速超过25倍。