Efficient Parallel Data Optimization for Homogeneous Diffusion Inpainting of 4K Images

TL;DR

This paper introduces fast GPU-accelerated algorithms for optimizing data in homogeneous diffusion inpainting, significantly improving quality and speed for 4K image reconstruction compared to previous methods.

Contribution

It presents novel parallel spatial and tonal optimization algorithms that leverage GPU computing and advanced numerical techniques for high-quality image inpainting.

Findings

Outperforms prior methods in runtime by a wide margin.

Produces high-quality inpainting masks for 4K images.

Efficiently utilizes GPU parallelism for optimization tasks.

Abstract

Homogeneous diffusion inpainting can reconstruct missing image areas with high quality from a sparse subset of known pixels, provided that their location as well as their gray or color values are well optimized. This property is exploited in inpainting-based image compression, which is a promising alternative to classical transform-based codecs such as JPEG and JPEG2000. However, optimizing the inpainting data is a challenging task. Current approaches are either fairly slow or do not produce high quality results. As a remedy we propose fast spatial and tonal optimization algorithms for homogeneous diffusion inpainting that efficiently utilize GPU parallelism, with a careful adaptation of some of the most successful numerical concepts. We propose a densification strategy using ideas from error-map dithering combined with a Delaunay triangulation for the spatial optimization. For the tonal optimization we design a domain decomposition solver that solves the corresponding normal equations in a matrix-free fashion and supplement it with a Voronoi-based initialization strategy. With our proposed methods we are able to generate high quality inpainting masks for homogeneous diffusion and optimized tonal values in a runtime that outperforms prior state-of-the-art by a wide margin.