论文标题
H-OWAN：张量1x1卷积的多段落图像恢复
H-OWAN: Multi-distorted Image Restoration with Tensor 1x1 Convolution
论文作者
论文摘要
通过结合扭曲的变形恢复其变体中的图像是一项具有挑战性的任务。在现有作品中，有前途的策略是应用并行的“操作”来处理不同类型的失真。但是，在特征融合阶段，由于特征的异质性通过不同的操作，少量操作将主导恢复结果。为此，我们通过施加高阶张量（外部）产品来介绍张量1x1卷积层，我们不仅可以统一异质特征，而且还考虑了额外的非线性。为了避免张量产物产生的不可接受的内核大小，我们用张量网络分解构建核，这能够将尺寸的指数增长转换为线性生长。在新层配备新层的情况下，我们提出了高级OWAN，以用于多延伸的图像修复。在数值实验中，提议的NET的表现优于先前的最先进，即使在更艰难的任务中也表现出了有希望的表现。
It is a challenging task to restore images from their variants with combined distortions. In the existing works, a promising strategy is to apply parallel "operations" to handle different types of distortion. However, in the feature fusion phase, a small number of operations would dominate the restoration result due to the features' heterogeneity by different operations. To this end, we introduce the tensor 1x1 convolutional layer by imposing high-order tensor (outer) product, by which we not only harmonize the heterogeneous features but also take additional non-linearity into account. To avoid the unacceptable kernel size resulted from the tensor product, we construct the kernels with tensor network decomposition, which is able to convert the exponential growth of the dimension to linear growth. Armed with the new layer, we propose High-order OWAN for multi-distorted image restoration. In the numerical experiments, the proposed net outperforms the previous state-of-the-art and shows promising performance even in more difficult tasks.
