Sparsity-based single image super resolution method generates the High-Resolution (HR) output via a corresponding dictionary from the Low-Resolution (LR) input. However, most of these existing methods ignore the complementary information from color channels, which causes the loss of a valid prior and the limitation of HR image quality improvement. In this paper, hypergraph regularization is first incorporated with Joint Color Dictionary Training (JCDT) model and HR image reconstruction (HRIR) model. A novel Hypergraph-regularized Sparse coding-based Super Resolution (HG-ScSR) is proposed. This regularization can not only focus on the illuminance information, but also exploit the self-channel and cross-channel information of three color RGB channels from high-resolution image patches. Especially, the complex relationship is explored among every color image patch pixel and the consistency of the similar pixels is enforced. Both simulated and real data experiments verify the higher performance of the proposed HG-ScSR.

基于稀疏性的单图像超分辨率方法通过低分辨率（LR）输入通过相应的词典生成高分辨率（HR）输出。然而，大多数这些现有方法忽略了来自彩色通道的补充信息，这导致有效先验的损失和HR图像质量提高的局限性。本文首先将超图正则化与联合颜色字典训练（JCDT）模型和HR图像重建（HRIR）模型结合在一起。提出了一种基于超图正则化稀疏编码的超分辨率（HG-ScSR）。这种正则化不仅可以集中在照度信息上，而且可以从高分辨率图像斑块中利用三个彩色RGB通道的自通道和跨通道信息。特别，在每个彩色图像补丁像素之间探索复杂的关系，并增强相似像素的一致性。模拟和真实数据实验均证明了所提出的HG-ScSR具有更高的性能。