Region-aware Attention for Image Inpainting
This work addresses image inpainting for computer vision applications, offering an incremental improvement over existing attention-based methods.
The paper tackles the problem of blurry content generation in attention-based image inpainting by proposing a region-aware attention module and learnable region dictionary, achieving superior results on datasets like CelebA, Places2, and Paris StreetView.
Recent attention-based image inpainting methods have made inspiring progress by modeling long-range dependencies within a single image. However, they tend to generate blurry contents since the correlation between each pixel pairs is always misled by ill-predicted features in holes. To handle this problem, we propose a novel region-aware attention (RA) module. By avoiding the directly calculating corralation between each pixel pair in a single samples and considering the correlation between different samples, the misleading of invalid information in holes can be avoided. Meanwhile, a learnable region dictionary (LRD) is introduced to store important information in the entire dataset, which not only simplifies correlation modeling, but also avoids information redundancy. By applying RA in our architecture, our methodscan generate semantically plausible results with realistic details. Extensive experiments on CelebA, Places2 and Paris StreetView datasets validate the superiority of our method compared with existing methods.