eduzhai > Applied Sciences > Engineering >

An Edge Information and Mask Shrinking Based Image Inpainting Approach

  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: In the image inpainting task, the ability to repair both high-frequency andlow-frequency information in the missing regions has a substantial influence onthe quality of the restored image. However, existing inpainting methods usuallyfail to consider both high-frequency and low-frequency informationsimultaneously. To solve this problem, this paper proposes edge information andmask shrinking based image inpainting approach, which consists of two models.The first model is an edge generation model used to generate complete edgeinformation from the damaged image, and the second model is an image completionmodel used to fix the missing regions with the generated edge information andthe valid contents of the damaged image. The mask shrinking strategy isemployed in the image completion model to track the areas to be repaired. Theproposed approach is evaluated qualitatively and quantitatively on the datasetPlaces2. The result shows our approach outperforms state-of-the-art methods.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×