
GraphBased Blind Image Deblurring From a Single Photograph
Blind image deblurring, i.e., deblurring without knowledge of the blur k...
read it

Spaceadaptive anisotropic bivariate Laplacian regularization for image restoration
In this paper we present a new regularization term for variational image...
read it

ADMMDIPTV: combining Total Variation and Deep Image Prior for image restoration
In the last decades, unsupervised deep learning based methods have caugh...
read it

Local Frequency Interpretation and NonLocal SelfSimilarity on Graph for Point Cloud Inpainting
As 3D scanning devices and depth sensors mature, point clouds have attra...
read it

Reversible Image Watermarking for Health Informatics Systems Using Distortion Compensation in Wavelet Domain
Reversible image watermarking guaranties restoration of both original co...
read it

Random Walk Graph Laplacian based Smoothness Prior for Soft Decoding of JPEG Images
Given the prevalence of JPEG compressed images, optimizing image reconst...
read it

Graph Signal Restoration Using Nested Deep Algorithm Unrolling
Graph signal processing is a ubiquitous task in many applications such a...
read it
NonLocal GraphBased Prediction For Reversible Data Hiding In Images
Reversible data hiding (RDH) is desirable in applications where both the hidden message and the cover medium need to be recovered without loss. Among many RDH approaches is predictionerror expansion (PEE), containing two steps: i) prediction of a target pixel value, and ii) embedding according to the value of predictionerror. In general, higher prediction performance leads to larger embedding capacity and/or lower signal distortion. Leveraging on recent advances in graph signal processing (GSP), we pose pixel prediction as a graphsignal restoration problem, where the appropriate edge weights of the underlying graph are computed using a similar patch searched in a semilocal neighborhood. Specifically, for each candidate patch, we first examine eigenvalues of its structure tensor to estimate its local smoothness. If sufficiently smooth, we pose a maximum a posteriori (MAP) problem using either a quadratic Laplacian regularizer or a graph total variation (GTV) term as signal prior. While the MAP problem using the first prior has a closedform solution, we design an efficient algorithm for the second prior using alternating direction method of multipliers (ADMM) with nested proximal gradient descent. Experimental results show that with better quality GSPbased prediction, at low capacity the visual quality of the embedded image exceeds stateoftheart methods noticeably.
READ FULL TEXT
Comments
There are no comments yet.