Screentone-Preserved Manga Retargeting

TL;DR

This paper introduces a novel manga retargeting method that preserves screentones during image rescaling, effectively reducing aliasing and blurriness, and ensuring high-quality visualization across various display resolutions.

Contribution

It presents the first manga retargeting approach that synthesizes rescaled images while maintaining screentone integrity using anchor-based proposals and a recurrent selection module.

Findings

Achieves superior visual quality compared to existing methods

Effectively reduces aliasing and blurriness in rescaled manga images

Demonstrates robustness across diverse resolutions

Abstract

As a popular comic style, manga offers a unique impression by utilizing a rich set of bitonal patterns, or screentones, for illustration. However, screentones can easily be contaminated with visual-unpleasant aliasing and/or blurriness after resampling, which harms its visualization on displays of diverse resolutions. To address this problem, we propose the first manga retargeting method that synthesizes a rescaled manga image while retaining the screentone in each screened region. This is a non-trivial task as accurate region-wise segmentation remains challenging. Fortunately, the rescaled manga shares the same region-wise screentone correspondences with the original manga, which enables us to simplify the screentone synthesis problem as an anchor-based proposals selection and rearrangement problem. Specifically, we design a novel manga sampling strategy to generate aliasing-free screentone proposals, based on hierarchical grid-based anchors that connect the correspondences between the original and the target rescaled manga. Furthermore, a Recurrent Proposal Selection Module (RPSM) is proposed to adaptively integrate these proposals for target screentone synthesis. Besides, to deal with the translation insensitivity nature of screentones, we propose a translation-invariant screentone loss to facilitate the training convergence. Extensive qualitative and quantitative experiments are conducted to verify the effectiveness of our method, and notably compelling results are achieved compared to existing alternative techniques.