Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Automatic example-based image colorization using location-aware cross-scale matching

Li, Bo, Lai, Yu-kun ORCID: https://orcid.org/0000-0002-2094-5680, John, Matthew and Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 2019. Automatic example-based image colorization using location-aware cross-scale matching. IEEE Transactions on Image Processing 28 (9) , pp. 4606-4619. 10.1109/TIP.2019.2912291

[thumbnail of color_cross_scale.pdf]
Preview
PDF - Accepted Post-Print Version
Download (31MB) | Preview

Abstract

Given a reference colour image and a destination grayscale image, this paper presents a novel automatic colourisation algorithm that transfers colour information from the reference image to the destination image. Since the reference and destination images may contain content at different or even varying scales (due to changes of distance between objects and the camera), existing texture matching based methods can often perform poorly. We propose a novel cross-scale texture matching method to improve the robustness and quality of the colourisation results. Suitable matching scales are considered locally, which are then fused using global optimisation that minimises both the matching errors and spatial change of scales. The minimisation is efficiently solved using a multi-label graph-cut algorithm. Since only low-level texture features are used, texture matching based colourisation can still produce semantically incorrect results, such as meadow appearing above the sky. We consider a class of semantic violation where the statistics of up-down relationships learnt from the reference image are violated and propose an effective method to identify and correct unreasonable colourisation. Finally, a novel nonlocal ℓ1 optimisation framework is developed to propagate high confidence micro-scribbles to regions of lower confidence to produce a fully colourised image. Qualitative and quantitative evaluations show that our method outperforms several state-of-the-art methods.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: IEEE
ISSN: 1057-7149
Date of First Compliant Deposit: 22 April 2019
Date of Acceptance: 5 April 2019
Last Modified: 07 Nov 2023 12:08
URI: https://orca.cardiff.ac.uk/id/eprint/121865

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics