Image Completion via Dual-path Cooperative Filtering
This addresses image completion for generating realistic content, but it appears incremental as it builds on predictive filtering methods.
The paper tackles the problem of poor cross-scene generalization and blurry artifacts in deep image completion by proposing a Dual-path Cooperative Filtering model, which outperforms state-of-the-art methods on three challenging datasets.
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.