Region-wise matching for image inpainting based on adaptive weighted low-rank decomposition

by   Shenghai Liao, et al.

Digital image inpainting is an interpolation problem, inferring the content in the missing (unknown) region to agree with the known region data such that the interpolated result fulfills some prior knowledge. Low-rank and nonlocal self-similarity are two important priors for image inpainting. Based on the nonlocal self-similarity assumption, an image is divided into overlapped square target patches (submatrices) and the similar patches of any target patch are reshaped as vectors and stacked into a patch matrix. Such a patch matrix usually enjoys a property of low rank or approximately low rank, and its missing entries are recoveried by low-rank matrix approximation (LRMA) algorithms. Traditionally, n nearest neighbor similar patches are searched within a local window centered at a target patch. However, for an image with missing lines, the generated patch matrix is prone to having entirely-missing rows such that the downstream low-rank model fails to reconstruct it well. To address this problem, we propose a region-wise matching (RwM) algorithm by dividing the neighborhood of a target patch into multiple subregions and then search the most similar one within each subregion. A non-convex weighted low-rank decomposition (NC-WLRD) model for LRMA is also proposed to reconstruct all degraded patch matrices grouped by the proposed RwM algorithm. We solve the proposed NC-WLRD model by the alternating direction method of multipliers (ADMM) and analyze the convergence in detail. Numerous experiments on line inpainting (entire-row/column missing) demonstrate the superiority of our method over other competitive inpainting algorithms. Unlike other low-rank-based matrix completion methods and inpainting algorithms, the proposed model NC-WLRD is also effective for removing random-valued impulse noise and structural noise (stripes).


page 6

page 9

page 10

page 11

page 12

page 13

page 15

page 16


Non-Local Robust Quaternion Matrix Completion for Large-Scale Color Images and Videos Inpainting

The image nonlocal self-similarity (NSS) prior refers to the fact that a...

Sparse + Low Rank Decomposition of Annihilating Filter-based Hankel Matrix for Impulse Noise Removal

Recently, so called annihilating filer-based low rank Hankel matrix (ALO...

Low rank prior and l0 norm to remove impulse noise in images

Patch-based low rank is an important prior assumption for image processi...

Restoration Guarantee of Image Inpainting via Low Rank Patch Matrix Completion

In recent years, patch-based image restoration approaches have demonstra...

Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting

Exemplar-based inpainting is the process of reconstructing missing parts...

Temporal Coherent and Graph Optimized Manifold Ranking for Visual Tracking

Recently, weighted patch representation has been widely studied for alle...

Generative Modeling in Structural-Hankel Domain for Color Image Inpainting

In recent years, some researchers focused on using a single image to obt...

Please sign up or login with your details

Forgot password? Click here to reset