HySim-IRIS: Hybrid similarity interactive restoration and inpainting suite
Year: 2025
Type: software-paper
Abstract: Image inpainting, the process of reconstructing missing or damaged regions in images, remains a critical challenge in computer vision with applications spanning medical imaging, remote sensing, and digital heritage preservation. While data-driven approaches dominate current research, model-driven methods retain significant value in scenarios with limited training data or specialized domain requirements. This paper presents HySim-IRIS, a hybrid similarity interactive restoration and inpainting suite, as a comprehensive GUI-based image inpainting application. The software features a novel hybrid similarity measure combining Chebyshev and Minkowski distances for patch-based inpainting, alongside a modern Qt-based interface with built-in mask editing tools, exhaustive parameter research capabilities, and comprehensive performance analytics. The application provides both CPU and GPU-accelerated implementations, with the latter achieving up to 20× speedup for high-resolution images.
Source: SoftwareX
Institution: International University of Rabat
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,200
OpenAlex ID: W4417416528