Hirarchical Digital Image Inpainting Using Wavelets
This work addresses image inpainting for applications like photo restoration, but it appears incremental as it builds on existing techniques with a hierarchical wavelet approach.
The paper tackles the challenge of inpainting large damaged areas in images by proposing a hierarchical algorithm using wavelets to separately handle structure and texture information, and it shows performance tested against existing methods like interpolation, diffusion, and exemplar techniques.
Inpainting is the technique of reconstructing unknown or damaged portions of an image in a visually plausible way. Inpainting algorithm automatically fills the damaged region in an image using the information available in undamaged region. Propagation of structure and texture information becomes a challenge as the size of damaged area increases. In this paper, a hierarchical inpainting algorithm using wavelets is proposed. The hierarchical method tries to keep the mask size smaller while wavelets help in handling the high pass structure information and low pass texture information separately. The performance of the proposed algorithm is tested using different factors. The results of our algorithm are compared with existing methods such as interpolation, diffusion and exemplar techniques.