3D convolutions are commonly employed by demosaicking neural models, in the same way as solving other image restoration problems. Counter-intuitively, we show that 3D convolutions implicitly impede the RGB color spectra from exchanging complementary information, resulting in spectral-inconsistent inference of the local spatial high frequency components. As a consequence, shallow 3D convolution networks suffer the Moir\'e artifacts, but deep 3D convolutions cause over-smoothness. We analyze the fundamental difference between demosaicking and other problems that predict lost pixels between available ones (e.g., super-resolution reconstruction), and present the underlying reasons for the confliction between Moir\'e-free and detail-preserving. From the new perspective, our work decouples the common standard convolution procedure to spectral and spatial feature aggregations, which allow strengthening global communication in the spectral dimension while respecting local contrast in the spatial dimension. We apply our demosaicking model to two tasks: Joint Demosaicking-Denoising and Independently Demosaicking. In both applications, our model substantially alleviates artifacts such as Moir\'e and over-smoothness at similar or lower computational cost to currently top-performing models, as validated by diverse evaluations. Source code will be released along with paper publication.

翻译：3D卷积通常被去马赛克神经网络模型采用，其方式与解决其他图像复原问题相同。然而，反直觉的是，我们发现3D卷积会隐式地阻碍RGB色彩光谱交换互补信息，导致局部空间高频分量预测出现光谱不一致性。因此，浅层3D卷积网络会产生摩尔纹伪影，而深层3D卷积则会导致过度平滑。我们分析了去马赛克问题与其他预测缺失像素问题（如超分辨率重建）之间的本质差异，并揭示了无摩尔纹与保细节之间矛盾的根本原因。基于这一新视角，我们的工作将标准卷积过程解耦为光谱特征聚合与空间特征聚合，从而在空间维度上保持局部对比度的同时，增强光谱维度的全局信息交换。我们将所提出的去马赛克模型应用于两个任务：联合去马赛克-去噪与独立去马赛克。在两类应用中，与当前性能最优的模型相比，我们的模型在相似或更低计算成本下显著减轻了摩尔纹、过度平滑等伪影，多项评估验证了其有效性。源代码将在论文发表时同步发布。