The next-generation radio-interferometric (RI) telescopes require imaging algorithms capable of forming high-resolution high-dynamic-range images from large data volumes spanning wide frequency bands. Recently, AIRI, a plug-and-play (PnP) approach taking the forward-backward algorithmic structure (FB), has demonstrated state-of-the-art performance in monochromatic RI imaging by alternating a data-fidelity step with a regularization step via learned denoisers. In this work, we introduce HyperAIRI, its hyperspectral extension, underpinned by learned hyperspectral denoisers enforcing a power-law spectral model. For each spectral channel, the HyperAIRI denoiser takes as input its current image estimate, alongside estimates of its two immediate neighboring channels and the spectral index map, and provides as output its associated denoised image. To ensure convergence of HyperAIRI, the denoisers are trained with a Jacobian regularization enforcing non-expansiveness. To accommodate varying dynamic ranges, we assemble a shelf of pre-trained denoisers, each tailored to a specific dynamic range. At each HyperAIRI iteration, the spectral channels of the target image cube are updated in parallel using dynamic-range-matched denoisers from the pre-trained shelf. The denoisers are also endowed with a spatial image faceting functionality, enabling scalability to varied image sizes. Additionally, we formally introduce Hyper-uSARA, a variant of the optimization-based algorithm HyperSARA, promoting joint sparsity across spectral channels via the $\ell_{2,1}$-norm, also adopting FB. We evaluate HyperAIRI's performance on simulated and real observations. We showcase its superior performance compared to its optimization-based counterpart Hyper-uSARA, CLEAN's hyperspectral variant in WSClean, and the monochromatic imaging algorithms AIRI and uSARA.

翻译：下一代射电干涉（RI）望远镜需要能够从覆盖宽频段的大规模数据中重建高分辨率、高动态范围图像的成像算法。最近，AIRI 作为一种采用前向后向算法结构（FB）的即插即用（PnP）方法，通过交替执行数据保真度步骤与基于学习去噪器的正则化步骤，在单色 RI 成像中展现了最先进的性能。本文中，我们介绍了其高光谱扩展版本 HyperAIRI，该方法以强制功率律光谱模型的学习型高光谱去噪器为基础。对于每个光谱通道，HyperAIRI 去噪器以当前图像估计值、其两个直接相邻通道的估计值以及光谱指数图作为输入，并输出相应的去噪后图像。为确保 HyperAIRI 的收敛性，去噪器在训练时采用了强制非扩张性的雅可比正则化。为适应不同的动态范围，我们构建了一个预训练去噪器库，其中每个去噪器都针对特定的动态范围进行定制。在每次 HyperAIRI 迭代中，目标图像立方体的光谱通道会使用预训练库中动态范围匹配的去噪器进行并行更新。这些去噪器还具备空间图像分块处理功能，从而能够适应不同的图像尺寸。此外，我们正式介绍了 Hyper-uSARA，它是基于优化的算法 HyperSARA 的一个变体，通过 $\ell_{2,1}$-范数促进光谱通道间的联合稀疏性，同样采用 FB 结构。我们在模拟和实际观测数据上评估了 HyperAIRI 的性能。结果表明，相较于其基于优化的对应算法 Hyper-uSARA、WSClean 中 CLEAN 的高光谱变体，以及单色成像算法 AIRI 和 uSARA，HyperAIRI 展现了更优越的性能。