Title:	On Unguided Automatic Colorization of Monochrome Images
Authors:	Sluzek, Andrzej
Citation:	WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 379-384.
Issue Date:	2023
Publisher:	Václav Skala - UNION Agency
Document type:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/54446
ISBN:	978-80-86943-32-9
ISSN:	2464–4617 (print) 2464–4625 (CD/DVD)
Keywords:	kolorování obrazu;odbarvování;modely rgb2grey;vizuální věrohodnost;barevné modely
Keywords in different language:	image colorization;decolorization;rgb2gray models;visual plausibility;color models
Abstract in different language:	Image colorization is a challenging problem due to the infinite RGB solutions for a grayscale picture. Therefore, human assistance, either directly or indirectly, is essential for achieving visually plausible colorization. This paper aims to perform colorization using only a grayscale image as the data source, without any reliance on metadata or human hints. The method assumes an (arbitrary) rgb2gray model and utilizes a few simple heuristics. Despite probabilistic elements, the results are visually acceptable and repeatable, making this approach feasible (e.g. for aesthetic purposes) in domains where only monochrome visual representations exist. The paper explains the method, presents exemplary results, and discusses a few supplementary issues.
Rights:	© Václav Skala - UNION Agency
Appears in Collections:	WSCG 2023: Full Papers Proceedings

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.