基于物理特征动态识别非线性混合作用区域，提升光谱解混精度。
Physics-Guided Regime Unmixing
- 通过像素级物理参数激活非线性混合，避免全局统一假设
- 在三个数据集上实现优于基线的解混效果，物理一致性超0.90
- 融合多种非线性模型并生成可解释的区域分布图，适合遥感应用
线性混合模型（LMM）因简洁性主导光谱解混，但在多重散射下失效；现有非线性模型则对全场景统一应用固定混合模式。本文提出物理引导的混合模式解混（PGRU），从可观测物理特征中估计像素级标量ξ_i ∈ [0,1]，仅在合理区域激活非线性混合。通过学习注意力机制融合广义双线性模型（GBM）、后非线性混合模型（PPNM）和Hapke模型的残差，生成可解释的混合模式图。在Samson、Jasper Ridge和Urban数据集上的实验显示，相比基线方法性能持续提升，物理一致性ρ > 0.90。
原文摘要 · Abstract (English)
The Linear Mixing Model (LMM) dominates spectral unmixing for its simplicity, but fails under multiple scattering; existing nonlinear models compensate by applying a fixed regime uniformly across entire scenes. We propose Physics-Guided Regime Unmixing (PGRU), which estimates a pixel-wise scalar $ξ_i \in [0,1]$ from observable physical features to activate nonlinear mixing only where justified. Residuals from the Generalized Bilinear Model (GBM), the Post-Nonlinear Mixing Model (PPNM), and Hapke are combined via learned attention, yielding interpretable regime maps. Experiments on Samson, Jasper Ridge, and Urban show consistent improvements over baselines, with physical coherence $ρ> 0.90$.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。