Domain Decomposition Algorithms for Real-time Homogeneous Diffusion Inpainting in 4K

TL;DR

This paper introduces a GPU-accelerated domain decomposition algorithm for real-time 4K image inpainting using homogeneous diffusion, significantly reducing computation time compared to previous methods.

Contribution

It adapts advanced domain decomposition algorithms, specifically an optimized restricted additive Schwarz method, for efficient parallel inpainting on GPUs, enabling real-time processing of high-resolution images.

Findings

Achieves real-time 4K inpainting on GPUs

Reduces computational cost compared to traditional methods

Maintains high-quality inpainting without block artifacts

Abstract

Inpainting-based compression methods are qualitatively promising alternatives to transform-based codecs, but they suffer from the high computational cost of the inpainting step. This prevents them from being applicable to time-critical scenarios such as real-time inpainting of 4K images. As a remedy, we adapt state-of-the-art numerical algorithms of domain decomposition type to this problem. They decompose the image domain into multiple overlapping blocks that can be inpainted in parallel by means of modern GPUs. In contrast to classical block decompositions such as the ones in JPEG, the global inpainting problem is solved without creating block artefacts. We consider the popular homogeneous diffusion inpainting and supplement it with a multilevel version of an optimised restricted additive Schwarz (ORAS) method that solves the local problems with a conjugate gradient algorithm. This enables us to perform real-time inpainting of 4K colour images on contemporary GPUs, which is substantially more efficient than previous algorithms for diffusion-based inpainting.