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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kämper, Niklas, Chizhov, Vassillen, Weickert, Joachim
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917746732695552
author Kämper, Niklas
Chizhov, Vassillen
Weickert, Joachim
author_facet Kämper, Niklas
Chizhov, Vassillen
Weickert, Joachim
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06747
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Parallel Data Optimization for Homogeneous Diffusion Inpainting of 4K Images
Kämper, Niklas
Chizhov, Vassillen
Weickert, Joachim
Image and Video Processing
Numerical Analysis
65N55, 65D18, 68U10, 94A08
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.
title Efficient Parallel Data Optimization for Homogeneous Diffusion Inpainting of 4K Images
topic Image and Video Processing
Numerical Analysis
65N55, 65D18, 68U10, 94A08
url https://arxiv.org/abs/2401.06747