Given the recent advances with image-generating algorithms, deep image completion methods have made significant progress. However, state-of-art methods typically provide poor cross-scene generalization, and generated masked areas often contain blurry artifacts. Predictive filtering is a method for restoring images, which predicts the most effective kernels based on the input scene. Motivated by this approach, we address image completion as a filtering problem. Deep feature-level semantic filtering is introduced to fill in missing information, while preserving local structure and generating visually realistic content. In particular, a Dual-path Cooperative Filtering (DCF) model is proposed, where one path predicts dynamic kernels, and the other path extracts multi-level features by using Fast Fourier Convolution to yield semantically coherent reconstructions. Experiments on three challenging image completion datasets show that our proposed DCF outperforms state-of-art methods.

翻译：随着图像生成算法的最新进展，深度图像补全方法取得了显著进步。然而，现有最先进方法通常存在跨场景泛化能力差的问题，且生成的掩膜区域常包含模糊伪影。预测滤波是一种图像复原方法，它根据输入场景预测最有效的卷积核。受该方法启发，我们将图像补全视为一个滤波问题。本文引入深度特征级语义滤波，在缺失信息填充过程中既保持局部结构，又生成视觉真实的内容。具体而言，我们提出双路协同滤波（DCF）模型：一路预测动态卷积核，另一路通过快速傅里叶卷积提取多层级特征，从而实现语义连贯的重建。在三个具有挑战性的图像补全数据集上的实验表明，我们提出的DCF模型性能优于现有最先进方法。