通过空间算子以任意尺度超分辨未见过的高光谱传感器
Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators
- Hefei University of Technology（合肥工业大学）
- National University of Singapore（新加坡国立大学）
- University of Michigan（密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出OmniHSR，通过预测共享频带的空间算子实现跨传感器任意尺度高光谱超分辨，仅0.538M参数，在未见数据集上优于直接迁移基线，PSNR提升0.55dB，推理加速36倍。
AI中文摘要：
在单一模型下实现跨传感器泛化和任意尺度重建，在高光谱超分辨（HSR）中仍然具有挑战性。尽管近期方法支持任意尺度重建，但将其应用于训练范围之外的新传感器或尺度时，通常需要额外的数据和计算来维持重建质量。为解决这些挑战，我们提出OmniHSR，它预测共享频带的空间算子而非光谱值。跨光谱映射（CSM）将任意波段数的输入重采样到固定参考位置，并预测具有高斯支撑的局部算子。连续算子场重建（COFR）将这些算子组合成连续场，并应用于所有原始波段以实现任意尺度重建。实验表明，在所有七个数据集上，算子预测优于直接光谱值预测。仅使用0.538M参数在ARAD上训练，OmniHSR在六个未见数据集上优于所有直接迁移的基线，无需目标域训练数据或适应。在从×2到×48的十二个上采样因子中，它在Pavia U和Chikusei上的平均PSNR比最强基线提高0.55 dB。它还超越了从零开始训练或适应目标传感器的基线，并实现了高达36倍的推理加速。我们的代码将很快公开发布。
英文摘要：
Achieving cross-sensor generalization and arbitrary-scale reconstruction with a single model remains challenging in hyperspectral super-resolution (HSR). Although recent methods support arbitrary-scale reconstruction, applying them to new sensors or scales beyond the training range often requires additional data and computation to maintain reconstruction quality. To address these challenges, we propose OmniHSR, which predicts band-shared spatial operators rather than spectral values. Cross-Spectral Mapping (CSM) resamples inputs with any number of bands to fixed reference positions and predicts local operators with Gaussian supports. Continuous Operator-Field Reconstruction (COFR) composes these operators into a continuous field and applies them to all original bands for arbitrary-scale reconstruction. Experiments demonstrate that operator prediction outperforms direct spectral-value prediction on all seven datasets. Trained solely on ARAD with only 0.538M parameters, OmniHSR outperforms all directly transferred baselines on six unseen datasets without target-domain training data or adaptation. Across twelve upsampling factors from $\times2$ to $\times48$, it improves average PSNR on Pavia U and Chikusei by 0.55 dB over the strongest baseline. It also surpasses baselines trained from scratch or adapted on the target sensor and achieves up to $36\times$ faster inference. Our code will be publicly released soon.
