Image Processing using Smooth Ordering of its Patches

Abstract

We propose an image processing scheme based on reordering of its patches. For a given corrupted image, we extract all patches with overlaps, refer to these as coordinates in high-dimensional space, and order them such that they are chained in the "shortest possible path", essentially solving the traveling salesman problem. The obtained ordering applied to the corrupted image, implies a permutation of the image pixels to what should be a regular signal. This enables us to obtain good recovery of the clean image by applying relatively simple 1D smoothing operations (such as filtering or interpolation) to the reordered set of pixels. We explore the use of the proposed approach to image denoising and inpainting, and show promising results in both cases.

8 pages, 7 figures, 4 tables, submitted to IEEE Transactions on Image Processing

Cited by in corpus (20)

• Smooth PARAFAC Decomposition for Tensor Completion
• Sparsity Based Poisson Denoising with Dictionary Learning
• Adaptive Image Denoising by Targeted Databases
• LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
• Restoration by Compression
• Patch-Ordering as a Regularization for Inverse Problems in Image Processing
• On a fast bilateral filtering formulation using functional rearrangements
• FRIST - Flipping and Rotation Invariant Sparsifying Transform Learning and Applications
• SNIPS: Solving Noisy Inverse Problems Stochastically
• Removing Multi-frame Gaussian Noise by Combining Patch-based Filters with Optical Flow
• The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling
• Good Similar Patches for Image Denoising
• A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization
• Image denoising with less artefacts: Novel non-linear filtering on fast patch reorderings
• Nonnegative Matrix Factorization applied to reordered pixels of single images based on patches to achieve structured nonnegative dictionaries
• Can fully convolutional networks perform well for general image restoration problems?
• Boosting of Image Denoising Algorithms
• Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting
• Super Resolution of Arctic Sea Ice Concentration
• From Group Sparse Coding to Rank Minimization: A Novel Denoising Model for Low-level Image Restoration