Compressing Images with Diffusion- and Exemplar-Based Inpainting

Diffusion-based image compression methods can surpass state-of-the-art transform coders like JPEG 2000 for cartoon-like images. However, they are not well-suited for highly textured image content. Recently, advances in exemplar-based inpainting have made it possible to reconstruct images with non-local methods from sparse known data. In our work we compare the performance of such exemplar-based and diffusion-based inpainting algorithms, dependent on the type of image content. We use our insights to construct a hybrid compression codec that combines the strengths of both approaches. Experiments demonstrate that our novel method offers significant advantages over state-of-the-art diffusion-based methods on textured image data and can compete with transform coders.