Here we use convex optimization to inpaint missing pixels in corrupted images. We find the discrete gradient and minimize its l1 norm under the constraint that the recovered image must match the corrupt image at those indices where the pixels are valid. I first saw this problem in a lecture by Stephen Boyd and Steven Diamond (Stanford).
-
Notifications
You must be signed in to change notification settings - Fork 0
jhultman/image-inpainting
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
About
Inpainting via convex optimization.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published