Sparse Inpainting with Smoothed Particle Hydrodynamics

TL;DR

This paper introduces a novel sparse image inpainting method using an adapted Smoothed Particle Hydrodynamics approach, incorporating spatial and data value optimization, and compares various kernels for improved performance.

Contribution

It modifies SPH for better constant and linear function reproduction and explores kernel and spatial optimizations for enhanced sparse inpainting results.

Findings

The modified SPH can effectively perform sparse inpainting.

Anisotropic kernels improve inpainting of oriented image features.

The proposed method competes with existing diffusion and exemplar-based techniques.

Abstract

Digital image inpainting refers to techniques used to reconstruct a damaged or incomplete image by exploiting available image information. The main goal of this work is to perform the image inpainting process from a set of sparsely distributed image samples with the Smoothed Particle Hydrodynamics (SPH) technique. As, in its naive formulation, the SPH technique is not even capable of reproducing constant functions, we modify the approach to obtain an approximation which can reproduce constant and linear functions. Furthermore, we examine the use of Voronoi tessellation for defining the necessary parameters in the SPH method as well as selecting optimally located image samples. In addition to this spatial optimization, optimization of data values is also implemented in order to further improve the results. Apart from a traditional Gaussian smoothing kernel, we assess the performance of other kernels on both random and spatially optimized masks. Since the use of isotropic smoothing kernels is not optimal in the presence of objects with a clear preferred orientation in the image, we also examine anisotropic smoothing kernels. Our final algorithm can compete with well-performing sparse inpainting techniques based on homogeneous or anisotropic diffusion processes as well as with exemplar-based approaches.