Manga Images Research Articles

Reference‐based Screentone Transfer via Pattern Correspondence and Regularization

AbstractAdding screentone to initial line drawings is a crucial step for manga generation, but is a tedious and human‐laborious task. In this work, we propose a novel data‐driven method aiming to transfer the screentone pattern from a reference manga image. This not only ensures the quality, but also adds controllability to the generated manga results. The reference‐based screentone translation task imposes several unique challenges. Since manga image often contains multiple screentone patterns interweaved with line drawing, as an abstract art, this makes it even more difficult to extract disentangled style code from the reference. Also, finding correspondence for mapping between the reference and the input line drawing without any screentone is hard. As screentone contains many subtle details, how to guarantee the style consistency to the reference remains challenging. To suit our purpose and resolve the above difficulties, we propose a novel Reference‐based Screentone Transfer Network (RSTN). We encode the screentone style through a 1D stylegram. A patch correspondence loss is designed to build a similarity mapping function for guiding the translation. To mitigate the generated artefacts, a pattern regularization loss is introduced in the patch‐level. Through extensive experiments and a user study, we have demonstrated the effectiveness of our proposed model.

Parsing-Conditioned Anime Translation: A New Dataset and Method

Anime is an abstract art form that is substantially different from the human portrait, leading to a challenging misaligned image translation problem that is beyond the capability of existing methods. This can be boiled down to a highly ambiguous unconstrained translation between two domains. To this end, we design a new anime translation framework by deriving the prior knowledge of a pre-trained StyleGAN model. We introduce disentangled encoders to separately embed structure and appearance information into the same latent code, governed by four tailored losses. Moreover, we develop a FaceBank aggregation method that leverages the generated data of the StyleGAN, anchoring the prediction to produce in-domain animes. To empower our model and promote the research of anime translation, we propose the first anime portrait parsing dataset, Danbooru-Parsing , containing 4,921 densely labeled images across 17 classes. This dataset connects the face semantics with appearances, enabling our new constrained translation setting. We further show the editability of our results, and extend our method to manga images, by generating the first manga parsing pseudo data. Extensive experiments demonstrate the values of our new dataset and method, resulting in the first feasible solution on anime translation.

Panel Extraction and Plane Background Estimation for Motion Comic Creation of Manga Image

Panel Extraction and Plane Background Estimation for Motion Comic Creation of Manga Image

Towards Fully Automated Manga Translation

We tackle the problem of machine translation of manga, Japanese comics. Manga translation involves two important problems in machine translation: context-aware and multimodal translation. Since text and images are mixed up in an unstructured fashion in Manga, obtaining context from the image is essential for manga translation. However, it is still an open problem how to extract context from image and integrate into MT models. In addition, corpus and benchmarks to train and evaluate such model is currently unavailable. In this paper, we make the following four contributions that establishes the foundation of manga translation research. First, we propose multimodal context-aware translation framework. We are the first to incorporate context information obtained from manga image. It enables us to translate texts in speech bubbles that cannot be translated without using context information (e.g., texts in other speech bubbles, gender of speakers, etc.). Second, for training the model, we propose the approach to automatic corpus construction from pairs of original manga and their translations, by which large parallel corpus can be constructed without any manual labeling. Third, we created a new benchmark to evaluate manga translation. Finally, on top of our proposed methods, we devised a first compleheisive system for fully automated manga translation.

Building a Manga Dataset “Manga109” With Annotations for Multimedia Applications

Manga, or comics, which are a type of multimodal artwork, have been left behind in the recent trend of deep learning applications because of the lack of a proper dataset. Hence, we built Manga109, a dataset consisting of a variety of 109 Japanese comic books (94 authors and 21,142 pages) and made it publicly available by obtaining author permissions for academic use. We carefully annotated the frames, speech texts, character faces, and character bodies; the total number of annotations exceeds 500k. This dataset provides numerous manga images and annotations, which will be beneficial for use in machine learning algorithms and their evaluation. In addition to academic use, we obtained further permission for a subset of the dataset for industrial use. In this article, we describe the details of the dataset and present a few examples of multimedia processing applications (detection, retrieval, and generation) that apply existing deep learning methods and are made possible by the dataset.

Boundary-aware texture region segmentation from manga

Due to the lack of color in manga (Japanese comics), black-and-white textures are often used to enrich visual experience. With the rising need to digitize manga, segmenting texture regions from manga has become an indispensable basis for almost all manga processing, from vectorization to colorization. Unfortunately, such texture segmentation is not easy since textures in manga are composed of lines and exhibit similar features to structural lines (contour lines). So currently, texture segmentation is still manually performed, which is labor-intensive and time-consuming. To extract a texture region, various texture features have been proposed for measuring texture similarity, but precise boundaries cannot be achieved since boundary pixels exhibit different features from inner pixels. In this paper, we propose a novel method which also adopts texture features to estimate texture regions. Unlike existing methods, the estimated texture region is only regarded an initial, imprecise texture region. We expand the initial texture region to the precise boundary based on local smoothness via a graph-cut formulation. This allows our method to extract texture regions with precise boundaries. We have applied our method to various manga images and satisfactory results were achieved in all cases.

Sketch-based manga retrieval using manga109 dataset

Manga (Japanese comics) are popular worldwide. However, current e-manga archives offer very limited search support, i.e., keyword-based search by title or author. To make the manga search experience more intuitive, efficient, and enjoyable, we propose a manga-specific image retrieval system. The proposed system consists of efficient margin labeling, edge orientation histogram feature description with screen tone removal, and approximate nearest-neighbor search using product quantization. For querying, the system provides a sketch-based interface. Based on the interface, two interactive reranking schemes are presented: relevance feedback and query retouch. For evaluation, we built a novel dataset of manga images, Manga109, which consists of 109 comic books of 21,142 pages drawn by professional manga artists. To the best of our knowledge, Manga109 is currently the biggest dataset of manga images available for research. Experimental results showed that the proposed framework is efficient and scalable (70 ms from 21,142 pages using a single computer with 204 MB RAM).

‘Blood, guts and Bambi eyes’: Urotsukidoji and the Transcultural Reception and Regulation of Anime

The regulation and reception of anime in Britain has, historically, been fraught with difficulty. In 1992, the British Board of Film Classification (BBFC) rejected the first instalment of Urotsukidoji, a controversial series of erotic anime, on the grounds of its sexually explicit content; this decision set a precedent for the way in which they would continue to censor anime for the following two decades. Nearly twenty years later, in 2009, Clause 62 of the Coroners and Justice Act, also colloquially known as the ‘Dangerous Cartoons Act’, made it a criminal offence to possess non-photographic pornographic images of children, including CGI, cartoons, manga images and drawings. Through an examination of the BBFC's archival materials on Urotsukidoji – Legend of the Overfiend, supplemented by references to a small number of newspaper articles published during this period, this article offers a range of insights into the historical context in which the current series of debates surrounding the ‘Dangerous Cartoons Act’ can be situated and assessed. These are used to consider the transcultural flow of genres across national borders, and the difficulties that a regulator from one culture encounters when dealing with controversial material originating from another, such as Japan, that has a substantially different set of social values and artistic conventions. Furthermore, this case highlights the important role played by distribution companies in shaping the production and evolution of genres within the transcultural marketplace.

KOUNO FUMIYO'S HIROSHIMA MANGA: A Style-Centered Attempt at Re-Reading

Kouno Fumiyo’s graphic narratives about Hiroshima, beginning with Yūnagi no machi, sakura no kuni (Town of Evening Calm, Country of Cherry Blossoms, 2004), have drawn attention as a new kind of A-bomb manga, but they have also met with harsh criticism by historians who privilege story and representational content when approaching manga. Against their charge of a lack of criticality, this review article highlights the critical potential of Kouno’s graphic narratives by focusing on how comics-specific style, especially paneling and linework, affects both narrative content and the act of reading. Kouno’s works exhibit a number of pecularities, ranging from what is drawn inside individual panels to the materiality of the line work marked, among other things, by the motif of the hand. The article demonstrates how these stylistic contrivances prompt not only re-reading, or revisiting both specific manga images and the represented past, but that they also allow for ‘touching’ the past. With respect to the latter, the article maintains, that Kouno’s manga promote a bodily kind of historical memory that implies an alternative to the exclusive concentration on thematic representation and ideological content. With respect to manga, the article emphasizes that critical potential arises to a significant extent from specific acts of reading facilitated by specific stylistic means.

Text-aware balloon extraction from manga

Manga, a Japanese word for comics, is a worldwide popular visual entertainment. Nowadays, electronic devices boost the fast development of motion manga for the purpose of visual richness and manga promotion. To convert static manga images into motion mangas, text balloons are usually animated individually for better story telling. This needs the artists to cut out each text balloon meticulously, and therefore it is quite labor-intensive and time-consuming. In this paper, we propose an automatic approach that can extract text balloons from manga images both accurately and effectively. Our approach starts by extracting white areas that contain texts as text blobs. Different from existing text blob extraction methods that only rely on shape properties, we incorporate text properties in order to differentiate text blobs from texture blobs. Instead of heuristic parameter thresholding, we achieve text blob classification via learning-based classifiers. Along with the novel text blob classification method, we also make the first attempt in trying to tackle the boundary issue in balloon extraction. We apply our method on various styles of mangas and comics with texts in different languages, and convincing results are obtained in all cases.

Manga Drawing as Stereotyped Aesthetics

Abstract This essay is based on findings of my longitudinal phenomenological research study conducted from 2006 to 2009. The aim of my study was to understand the manga drawings produced by young adolescents in Hong Kong. Based on my findings, I present the argument that these adolescents have derived a conception of beauty from the manga images they have seen in popular visual culture, and that they have the ability to connect this concept with their life experiences. I also argue that their manga productions assist these students in making sense of the world around them.

Research on Mobile Terminal Based Real-Time Retargeting Technique for Manga Images

With the rapid growth of mobile terminal diversity and versatility, manual generation and maintenance of different versions of a manga image are currently required in mobile phone animation industry to achieve best display effect on various terminal configurations. This paper does researches on the real-time retargeting technique for manga images. By generating the importance map and analyzing the redundancy of feature lines in the manga image, combined with a retargeting algorithm, the solution proposed in this paper can solve the real-time retargeting of manga images on mobile terminals. For most of manga images, this solution can automatically generate a good resizing image with its key object outstanding based on screen resolution and size of the target terminal in real time.

States of Emergency: Urban Space and the Robotic Body in the <i>Metropolis</i> Tales

States of Emergency: Urban Space and the Robotic Body in the Metropolis Tales Lawrence Bird (bio) The tradition of the oppressed shows us that the “state of emergency” in which we live is not the exception but the rule. —Walter Benjamin, “Theses on the Philosophy of History” One of the most ubiquitous and disturbing images in anime and manga—indeed, an image that comes close to defining them—is the apocalyptic destruction of the city, with a human or humanoid figure at the epicenter. Very often this figure shares in the destruction of the city: it comes apart as the city does. This mutually experienced destruction implies more than just catastrophe. Whether we are aware of it or not, bodies and cities act as each other’s limits. On the one hand cities and buildings, as they shelter and enclose us, articulate a series of important distinctions. They mark a boundary between the spaces of the individual and those of the public. They afford a distinction between the space of citizens (often associated with the human) and the space beyond citizens, beyond civilization (the realms of the inhuman). On the other hand, our bodies in turn place limits on the city. Architecture and urban form take the human as their measure, literally and metaphorically. The shared destruction of these mutually delimiting figures—human [End Page 127] and urban architectures—implies a modern crisis in what it means to be human and what it means to dwell together in a community. Such images are all the more disturbing in their resonance with world events, which have with increasing frequency made us witnesses to the disintegration of real bodies, real cities. This implies some relation between anime and manga images of destruction and the history of destruction of cities in the real world. Particularly important in Japan is the leveling of cities at the end of World War II.1 Nonetheless, neither the imagery nor the circumstances for such imagery is uniquely Japanese. Both speak to a more general crisis of modernity, and to the political, social, and ontological implications of modernity as articulated in architectural form. Here I propose a look at three instances of the destruction of the modern city and its relation to the disintegration of the human, all of which strive to topple the same behemoth, the modern Metropolis. The first attempt on the Metropolis is Fritz Lang’s Metropolis (1927), a silent film that has had such a profound impact on the dystopian imagination in science fiction. Although Lang’s film toys with the possibility of the total destruction of the city, it ultimately offers something else: the immolation of a humanoid body, the sacrifice of a gynoid robot. Something similar occurs at the end of Tezuka Osamu’s manga Metropolis (1949): while the rebellion of the robots threatens to destroy the Metropolis, ultimately it is the robot that disintegrates. The connection between Lang’s and Tezuka’s tales is tenuous. By his own account, Tezuka had seen only one still from Lang’s film, and knew little else about its content.2 Tezuka was not rewriting or remaking Lang’s film, and the two stories differ significantly, as I will discuss below. Nonetheless, Tezuka and Lang are both concerned with the destructive forces of modernity and the potential obliteration of the very emblem of modernity, the Metropolis. It is on the basis of this shared concern for the modern destruction of body/city that director Rintarō and writer Ōtomo Katsuhiro’s animated Metropolis (2001) folds together elements of the two prior Metropolis stories. The 2001 version achieves the urban apocalypse only promised in the prior attempts, ending with the destruction of the gynoid robot and the Metropolis. Clearly, with the destruction of both the modern city and the human body at stake, there are political implications to such stories and images. In fact, each Metropolis presents a political scenario: the destruction of the city is linked to conflicts between factions and social classes as well as to the rise and fall of leaders. There is a direct engagement with structures of authority and sovereignty. Significantly, structures of authority [End Page 128] and sovereignty are imagined through...