Constrained texture restoration
Summary: A method is proposed for filling in missing areas of degraded images through explicit structure reconstruction, followed by texture synthesis. The structure being reconstructed represents meaningful edges from the image, which are traced inside the artefact. The structure reconstruction step relies on different properties of the edges touching the artefact and of the areas between them, in order to sketch the missing edges within the artefact area. The texture synthesis step is based on Markov random fields and is constrained by the traced edges in order to preserve both the shape and the appearance of the various regions in the image. The novelty of our contribution concerns constraining the texture synthesis, which proves to give results superior to the original texture synthesis alone, or to the smoothness-preserving structure-based restoration.
- Variational, Geometric, and Level Set Methods in Computer Vision
- STRUCTURE AND TEXTURE IMAGE INPAINTING USING SPARSE REPRESENTATIONS AND AN ITERATIVE CURVELET THRESHOLDING APPROACH
- Computer Vision - ECCV 2004
- Image completion based on automatic structure propagation
- Filling-in by joint interpolation of vector fields and gray levels
This page was built for publication: Constrained texture restoration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2502845)