Code for "CUBE: Curvature Regularization Via Weighted Nonlocal BiHarmonic"
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.github/ISSUE_TEMPLATE
Denoising
Fig
Inpainting
Semisupervise
CONTRIBUTING.md
CUBELOGO.png
LICENSE
README.md

README.md

Github Repository For CURE

Regularize The Curvature Of Patch Manifold Via Biharmonic Extension

Code for "CURE: Curvature Regularization Via Weighted Nonlocal BiHarmonic For Missing Data Recovery"

Requirement:

Image Inpainting

(Ground Turth, Inpainting, Sample Rate:20%)

(Ground Turth, W-CUBE:28.56dB, WNLL:27.78dB)

PSNR

SSIM

Semi-supervised Learning

In our test, we label 700, 100, 70, 50 and 35 images in MNIST respectively. The labeled images are selected at random in 70,000 images. For each sampling rate, we take 10 different random samples for comparisons.

Image Denoising

On going work.....