The progress on Hyperspectral image (HSI) super-resolution (SR) is still lagging behind the research of RGB image SR. HSIs usually have a high number of spectral bands, so accurately modeling spectral band interaction for HSI SR is hard. Also, training data for HSI SR is hard to obtain so the dataset is usually rather small. In this work, we propose a new test-time training method to tackle this problem. Specifically, a novel self-training framework is developed, where more accurate pseudo-labels and more accurate LR-HR relationships are generated so that the model can be further trained with them to improve performance. In order to better support our test-time training method, we also propose a new network architecture to learn HSI SR without modeling spectral band interaction and propose a new data augmentation method Spectral Mixup to increase the diversity of the training data at test time. We also collect a new HSI dataset with a diverse set of images of interesting objects ranging from food to vegetation, to materials, and to general scenes. Extensive experiments on multiple datasets show that our method can improve the performance of pre-trained models significantly after test-time training and outperform competing methods significantly for HSI SR.

翻译：高光谱图像（HSI）超分辨率（SR）的研究进展仍滞后于RGB图像超分辨率的研究。高光谱图像通常具有大量光谱波段，因此准确建模光谱波段间的相互作用以实现HSI超分辨率具有挑战性。此外，HSI超分辨率的训练数据难以获取，导致数据集通常较小。本研究提出一种新的测试时训练方法以应对此问题。具体而言，我们开发了一种新颖的自训练框架，通过生成更精确的伪标签和更准确的低分辨率-高分辨率映射关系，使模型能够利用这些数据进行进一步训练以提升性能。为更好地支持测试时训练方法，我们还提出一种无需建模光谱波段相互作用的新型网络架构来学习HSI超分辨率，并提出新的数据增强方法Spectral Mixup以在测试时增加训练数据的多样性。同时，我们收集了一个新的高光谱图像数据集，涵盖从食品、植被到材料及通用场景的多样化目标图像。在多个数据集上的大量实验表明，我们的方法能通过测试时训练显著提升预训练模型的性能，并在HSI超分辨率任务中明显优于现有方法。