The camera response function (CRF) that projects hyperspectral radiance to the corresponding RGB images is important for most hyperspectral image super-resolution (HSI-SR) models. In contrast to most studies that focus on improving HSI-SR performance through new architectures, we aim to prevent the model performance drop by learning the CRF of any given HSIs and RGB image from the same scene in an unsupervised manner, independent of the HSI-SR network. Accordingly, we first decompose the given RGB image into endmembers and an abundance map using the Dirichlet autoencoder architecture. Thereafter, a linear CRF learning network is optimized to project the reference HSIs to the RGB image that can be similarly decomposed like the given RGB, assuming that objects in both images share the same endmembers and abundance map. The quality of the RGB images generated from the learned CRFs is compared with that of the corresponding ground-truth images based on the true CRFs of two consumer-level cameras Nikon 700D and Canon 500D. We demonstrate that the effectively learned CRFs can prevent significant performance drop in three popular HSI-SR models on RGB images from different categories of standard datasets of CAVE, ICVL, Chikusei, Cuprite, Salinas, and KSC. The successfully learned CRF using the method proposed in this study would largely promote a wider implementation of HSI-SR models since tremendous performance drop can be prevented practically.

中文翻译：

---

端元辅助相机响应函数学习，提高高光谱图像超分辨率性能


将高光谱辐射亮度投射到相应 RGB 图像的相机响应函数 (CRF) 对于大多数高光谱图像超分辨率 (HSI-SR) 模型非常重要。与大多数专注于通过新架构提高 HSI-SR 性能的研究相比，我们的目标是通过以无监督的方式（独立于 HSI）学习同一场景中任何给定 HSI 和 RGB 图像的 CRF 来防止模型性能下降。 SR网络。因此，我们首先使用狄利克雷自动编码器架构将给定的 RGB 图像分解为端元和丰度图。此后，线性 CRF 学习网络被优化，将参考 HSI 投影到 RGB 图像，该图像可以像给定的 RGB 一样进行类似的分解，假设两个图像中的对象共享相同的端元和丰度图。将学习到的 CRF 生成的 RGB 图像的质量与基于两台消费级相机 Nikon 700D 和 Canon 500D 的真实 CRF 的相应地面实况图像的质量进行比较。我们证明，有效学习的 CRF 可以防止三种流行的 HSI-SR 模型在来自不同类别的标准数据集 CAVE、ICVL、Chikusei、Cuprite、Salinas 和 KSC 的 RGB 图像上出现性能显着下降。使用本研究中提出的方法成功学习的 CRF 将在很大程度上促进 HSI-SR 模型的更广泛实施，因为实际上可以防止巨大的性能下降。