Cartoon Style Research Articles

TSGAN: A two-stage interpretable learning method for image cartoonization

Interpreting style transfer methods and generating high-quality style images are two challenging computer vision tasks. However, most of the current image style transfer methods are inexplicable, and their image cartoonilation performance is also not satisfactory due to the complex lines and rich abstract features of cartoon style. To alleviate these two issues, in this paper we propose a novel two-stage interpretable learning method, the two-stage generative adversarial network (TSGAN), for image cartoonization. Particularly, we first divide the generative model into a content learning stage and a stylization stage. The advantages are twofold. The first is that the finely differentiated two-stage image generation model has better interpretability and easy understanding. The second is that TSGAN can adjust the content and style details of the generated image. We further propose a Cartoon Image Enhance (CIE) module for dynamically sampling salient cartoon texture details from training data to generate cartoon images with higher quality. Experimental results show that our TSGAN is effective when compared with four representative methods in terms of visual, qualitative, and quantitative comparisons and user research.

Caster: Cartoon style transfer via dynamic cartoon style casting

The cartoon style transfer has attracted widespread attention. Although many researchers have proposed various methods to develop this field, there are still two areas for improvement: (1) existing image-to-image cartoon style transfer methods can only perform domain-to-domain cartoon style transfer, neglecting the specific color and texture of the cartoon images, and (2) arbitrary style transfer methods only transfer the style of the style image onto the content image, neglecting the style information of the style domain. To address these issues, we observe that artists often refer to specific paintings to fine-tune the color of their artworks. This behavior inspires us to propose a method that can dynamically encode the style information of a specific cartoon image based on Variational Autoencoders, allowing the style feature to be cast onto the content feature dynamically. We also introduce a cartoon contrastive learning loss to push the cartoon stylized image closer to the same cartoon stylized image and otherwise pull away. Extensive experiments demonstrate that our proposed method, Caster, can generate a high-quality stylized image with specific and domain cartoon style information than state-of-the-art cartoon style transfer methods.

Cartoon-Style Poster Maps of Trans Continental Cartographers Ltd., Vancouver, B.C.

This article provides information about the stylized poster maps created in the late 1960s and early 1970s by Trans Continental Cartographers Ltd., Vancouver, B.C. These maps, which depicted cities across Canada and the United States, contained pictorial views of popular landmarks, buildings and places of interest. The restaurants, shops, stores and other attractions portrayed often paid an advertising fee to be represented on Trans Continental’s “city character maps,” which were drawn in a quirky and humorous cartoon style at an enlarged scale.

ANALISIS PERUBAHAN VISUAL KARAKTER PADA GIM COOKIE RUN KINGDOM

Cookies Character Design Development Analysis in Cookie Run Kingdom When viewed statistically on the play store, City-building Simulation Role Playing Games such as Cookie Run Kingdom are a type of game that is quite popular among players. The visualization is interesting, especially in the character design which uses an anthropomorphic style from the basic shape of the GingerBread Man cookie, which is one of the aspects that sells even though it uses an unusual style like anime and cartoon styles in general games. However, this popular character design can actually experience significant changes from visualization to character stories (lore) when it gets the influence of mixing from other elements and still gets a good response from the players. These changes to the character design will be further dissected to explore the elements that are mixed and removed in the character to create a new design. The shape matrix of the manga matrix technique will be used to dissect the elements that become the mix of cookie character designs, so that the results of the research can be used as reference material for character designers to use the manga matrix approach, which is reinforced by anthropomorphism techniques in creating new characters or redesigning them. unique, using a style that is not common but still captivates players. Keywords: character design, antropohomorfism, game, manga matrix

Instagram feeds design to invite and guide to do ‘Saat Teduh’ for Christian youth

The development of digital world technology is increasingly popular today, which causes teenagers to be faced with challenges and temptations to enjoy entertainment that no longer prioritizes worship and spiritual discipline. One of the spiritual disciplines is to do devotional time to help Christian youth build positive behavior in accordance with the teachings of the Bible. However, Christian teenagers find it difficult to do devotional time regularly and often feel bored when doing devotional time. This design was made to interest Christian teenagers to do devotional time and encourage them to be able to apply it regularly. This design uses research methods with a qualitative perspective, with interview and observation data collection techniques. Collecting data on devotional time, the behavior of Christian youth in Indonesia, the use of Instagram social media, and illustration techniques as a media approach. The illustration style uses cartoon style to interest Christian youth. The media approach uses post-modernism theory by using new ways to introduce devotional time that is increasingly being forgotten in modern days. The results of the design are in the form of Instagram feeds that provide contents about introduction, invitations, and guidance to do devotional time with character illustrations. Hopefully through this design, Christian teens can start taking their time to do devotional time.

ILLUSTRATION DESIGN OF THE AUTOBIOGRAPHY BOOK “THE WOUNDS THAT NEVER BLEED”

Human psychic development has different levels. A person will grow in harmony with his environment. However, for some people who have certain conditions it will be difficult to do this. This problem can lead to mental illness disorders. The author, who is a survivor, feels that people still consider this issue as a taboo problem. Therefore, the author was inspired to make an illustrative autobiographical book that tells the author's life story as a mental illness survivor. The stages of making this book consist of script writing, sketching, lineart, coloring, book layout and finishing. The contents in the book include the author's story with mental illness, GAD, Anorexia, OCD and Depression. The style used is a cartoon style to display expressive visual elements so that readers will easily understand the meaning inside it. The author uses pastel colors to give a soft and comfortable impression to the reader. The author also uses several points of view such as Long Shot, High View, Low View and Medium Shot to give dinamic style. This book will be an intermediary that brings readers and mental illness survivors to help both parties understand the importance of mental health.

ANALISIS VISUAL ILUSTRASI ANIMASI PADA IKLAN TVC DJARUM BEASISWA BULUTANGKIS 2018

TVC Djarum badminton scholarship 2018 advertisement is the only TVC PB Djarum that applies 2D animation, since TVC Djarum badminton scholarship has existed since 2007. This TVC’s 2018 was able to get the highest number of viewers on the official account of PB Djarum's Youtube platform. Thus, it was found the effect of animation on this TVC. Visually, the 2D animation in this TVC depicts children's characters and figures. This study aims to analyze how 2D animation in the form of illustrations of children playing badminton is applied to this TVC advertisement. Analysis of the application of this animation can examine the visualization of meaning, uniqueness, colors used, and the role of the illustration itself. The purpose of this study was to determine the character and meaning of the animation applied to the 2018 TVC Djarum Badminton Scholarship ad. literature review. This study found that TVC videos targeting the children's category would be better off using a 2D animation approach, using a cartoon style, and displaying color visuals that are impressively cheerful, enthusiastic, active, and courageous.

Effective Mode of Learning Cartonization: White-box Cartoon Representations

Cartoon, a renowned art form has different forms of application in various scenarios. In essence, different cartoon styles and use cases, demand prior knowledge to develop a usable algorithm or they have certain assumptions that needs to developed which cater to a particular task. The present paper’s objective is to determine an impactful approach towards image cartoonization, by developing an efficient and effective mode of such learning. The author proposes to identify three white-box representations from images individually, namely, the surface representation that covers a smooth surface of cartoon images, the structure representation that observes the sparse color-blocks and the texture representation which observes high- frequency texture, contours, details in cartoon images. The objectives of the proposed method are separately based on each extracted representations, that applies a Generative Adversarial Network (GAN) framework to understand the extracted representations and cartoonize images, which further enables the framework to be under control and adjustable at the convenience of the author. The present approach aspires to benefit the requirements of an artist that deals in several cases and has various style requirements. The author has conducted analytical and doctrinal studies, coupled with bibliometric research, that covers both quantitative analysis and qualitative comparisons, accompanied with the empirical study that have been present in several research papers, related to the subject have been thoroughly analyzed by the researcher to add something to existing knowledge on White box Cartoon Representations. Lastly, it is observed that the ablation study carried out shall showcase an influence of each component in the framework suggested by the author.

How to start a Focus Group: Using cartoons in adult focus groups to discuss consumers feedback expectations in food service settings

This article tests a novel method for starting focus groups quickly while ensuring that respondents understand the topic of interest for the study.To kick start the focus groups, a cartoon style illustration was developed. The cartoons depicted various food service experience from start to finish. Respondents first task was to indicate when it was natural for them to give feedback on the food service experience.The results show that the cartoons allowed respondents to quickly understand the topic, which in turn gave them confidence to contribute with relevant information from the start. In addition, respondents used the framework of the illustrations to keep the discussion focused on the topic throughout.We generally find that it is getting harder to find people who are willing to commit to 2 h focus groups after work. For us to find participants who are willing to take part, we are having to be much more time conscious, this method allows for shorter groups without losing valuable information.The method has a potential when it comes to testing food products as well as in the development of dishes for gastronomic experiences. It may also be a good tool to use in sensory focus groups.The use of comics to start off the focus group worked well in the context of a non-sensitive topic, in this case food service experiences. Further research could explore using this method for more sensitive topics.

PortraitNET: Photo-realistic portrait cartoon style transfer with self-supervised semantic supervision

We propose a novel framework to transfer the portrait image into its correspondence with photo-realistic and cartoon style. The existing work on neural style transfer conducts impressive results on artistic style transfer; however, the lack of semantic clues will lead to the color artifacts in photo-realistic style transfer because of the complex background and noise issues. In this work, we re-define the semantics as the pixel motion field according to the color displacement between adjacent animation frames along the optical direction and initiatively propose the self-supervised semantic network (SSNet) to learn semantic maps without human inference or any priories. The SSNet shares parameters with the style transfer network; thus, the superior alternatives can preserve the semantic completeness in the styled image. To solve the content missing and blur problems common in NST, we propose the bilateral convolution block (B-block) and feature fusion strategy (F-block) for visual smoothness to meet the perceptive satisfaction. The ablation studies are provided to validate the effectiveness, and comparative experiments with the state-of-the-art baselines demonstrate the advantages of the proposed method.

GAN-Based Multi-Style Photo Cartoonization.

Cartoon is a common form of art in our daily life and automatic generation of cartoon images from photos is highly desirable. However, state-of-the-art single-style methods can only generate one style of cartoon images from photos and existing multi-style image style transfer methods still struggle to produce high-quality cartoon images due to their highly simplified and abstract nature. In this article, we propose a novel multi-style generative adversarial network (GAN) architecture, called MS-CartoonGAN, which can transform photos into multiple cartoon styles. MS-CartoonGAN uses only unpaired photos and cartoon images of multiple styles for training. To achieve this, we propose to use (1) a hierarchical semantic loss with sparse regularization to retain semantic content and recover flat shading in different abstract levels, (2) a new edge-promoting adversarial loss for producing fine edges, and (3) a style loss to enhance the difference between output cartoon styles and make training process more stable. We also develop a multi-domain architecture, where the generator consists of a shared encoder and multiple decoders for different cartoon styles, along with multiple discriminators for individual styles. By observing that cartoon images drawn by different artists have their unique styles while sharing some common characteristics, our shared network architecture exploits the common characteristics of cartoon styles, achieving better cartoonization and being more efficient than single-style cartoonization. We show that our multi-domain architecture can theoretically guarantee to output desired multiple cartoon styles. Through extensive experiments including a user study, we demonstrate the superiority of the proposed method, outperforming state-of-the-art single-style and multi-style image style transfer methods.

Animation of two-dimensional pictorial works into multipurpose three-dimensional object. The Atlas of the ships of the known world depicted in the 1460 Fra Mauro’s Mappa Mundi as a showcase

This paper reports the preliminary results of an ongoing interdisciplinary research in digital humanities and animation that the authors are undertaking to explore how a new generation of three-dimensional (3D) non-photorealistic animated visualisations can improve upon two-dimensional (2D) visualisation methods. The outcomes of this research are enhancing both the studies and the user experience of digital representations of pictorial works that are seen as visual aggregators of human knowledge and experiences, because the sketching style and techniques of the artists are fully reproduced and made available to different interpretations. The mid-fifteenth-century atlas of the ships of the known world depicted in the Fra Mauro’s mappa mundi (Venice, Marciana National Library) has been used to: 1) showcase the design process and techniques of an innovative method through the prototyping of a 3D non-photorealistic-rendering (NPR) model of one ship, and 2) demonstrate the effectiveness of this method through the 3D NPR animation of all Fra Mauro’s ships as a contribution to both the advancement of learning in pre-modern maritime history (with a focus on shipping), and the implementation of NPR for the creative industry. These models are multiple purpose, because once they are created and implemented, the data can be displayed in different platforms (e.g., smart device, computer or larger flat screen, holographic pyramid, virtual reality, augmented reality, 3D printing).

SmartPaint: a co-creative drawing system based on generative adversarial networks

Artificial intelligence (AI) has played a significant role in imitating and producing large-scale designs such as e-commerce banners. However, it is less successful at creative and collaborative design outputs. Most humans express their ideas as rough sketches, and lack the professional skills to complete pleasing paintings. Existing AI approaches have failed to convert varied user sketches into artistically beautiful paintings while preserving their semantic concepts. To bridge this gap, we have developed SmartPaint, a co-creative drawing system based on generative adversarial networks (GANs), enabling a machine and a human being to collaborate in cartoon landscape painting. SmartPaint trains a GAN using triples of cartoon images, their corresponding semantic label maps, and edge detection maps. The machine can then simultaneously understand the cartoon style and semantics, along with the spatial relationships among the objects in the landscape images. The trained system receives a sketch as a semantic label map input, and automatically synthesizes its edge map for stable handling of varied sketches. It then outputs a creative and fine painting with the appropriate style corresponding to the human’s sketch. Experiments confirmed that the proposed SmartPaint system successfully generates high-quality cartoon paintings.

Exaggerated Cartoon Style Motion in Hotel Transylvania

The fundamental principles of animation were developed at the Disney studio in the 1930s and when applied to animation result in a recognisable “Disney” style of motion. By adhering to these fundamental principles of animation, Animators have been able to successfully extend the Disney style of motion to the 3D CG medium. This paper goes beyond Disney style motion and examines the adaptation of techniques typically seen in more extreme cartoon-style motion and “pushed posing”, exemplified by early Warner Brothers animated short films. This is achieved via an analysis of Hotel Transylvania by Sony Pictures Animation, which features a stylised form of animation adapted from the extended principles of extreme cartoon-style motion to the 3D medium.

Women’s Experimental Writing: Negative Aesthetics and Feminist Critique. Ellen E. Berry. London: Bloomsbury Publishing, 2016. Pp. 176.

<i>Women’s Experimental Writing: Negative Aesthetics and Feminist Critique</i>. Ellen E. Berry. London: Bloomsbury Publishing, 2016. Pp. 176.

Interrupting Chicken and the Elephant of Surprise by D. Stein

Stein, David E. Interrupting Chicken and the Elephant of Surprise. Candlewick Press in Association with Penguin Random House Canada, 2018.&#x0D; In this, his second picture book starring Interrupting Chicken, Stein begins with a delightful pun: Chicken declares that every good story has “an elephant of surprise.” Papa tries to convince her that she has misheard her teacher, that every good story has “…an element of surprise.” To demonstrate, he attempts to read aloud classic folk and fairy tales: The Ugly Duckling; Little Mermaid; Rapunzel. Chicken, of course, interrupts. The Ugly Duckling gazes at his reflection and sees “…an Elephant.” The prince ascends the tower on a rope of hair to discover that his love is “…an ELEPHANT!”. Papa is dogged; he keeps trying. Chicken is relentless; she keeps interrupting. The story hour goes on with appealing silliness until Papa graciously allows it to end, not surprisingly, with elephants.&#x0D; A former Caldecott Honor winner, Stein creates not only this amusing storyline, but its illustration as well. He employs a variety of artistic techniques to great effect. The basic narrative, (including Chicken’s interruptions of Papa’s readings) is presented in cartoon style and bold crayon; the classic readings are highlighted with line drawings and water colour. Thus the theme of “interruption” is both conveyed and sustained by the art work.&#x0D; There are a few provisos about sharing this book with primary school children: a child will more fully enjoy the inappropriateness—and silliness—of Chicken’s outbursts if he or she is familiar with the plotlines of the classic tales that Papa attempts to read. The wise parent, or teacher, or librarian will ensure this familiarity in the most obvious and enjoyable way: sharing the stories. There is a further consideration: the hilarity of Chicken’s behaviour arises because she either cannot, or will not, acknowledge the literary concept of a “surprise element.” Children who, themselves, can grasp that concept will laugh harder than children who cannot. Depending on the age and maturity of the child listener, a little didacticism on the part of the adult reader may be appropriate. With these requirements satisfied, this book is a winner.&#x0D; Recommended: 3 out of 4 stars Reviewer: Leslie Aitken&#x0D; Leslie Aitken’s long career in librarianship included selection of children’s literature for school, public, special, and academic libraries. She is a former Curriculum Librarian of the University of Alberta.

A Novel Pencil Drawing Algorithm Based on Non-Symmetry and Anti-Packing Pattern Representation Model

The artistic stylization transformation of images is an important part in the research of Non-Photorealistic Rendering (NPR). This kind of non-realistic stylized research has a very strong realistic romantic temperament and it can express the artistic pursuit of researchers very well. It is a good example of practical application combining computer science and art. In the technology of image style conversion, the simulation of the realistic art style includes mainly cartoon style, oil painting style, ink painting style and pencil drawing style. Previously, some researchers proposed a style conversion method based on the prior knowledge that there might be crosses at the junction of two lines where the tone distribution has a certain rule. However, in this paper, we have focused on the use of an edge extraction algorithm based on Non-symmetry and Anti-packing pattern representation Model (NAM) to enhance the pencil strokes and highlight the details of the image. Then, by combining the line pencil strokes with the tone drawing, we can transform the image into an image with pencil sketch style. Finally, compared with the most important previous methods, the experimental results presented in this paper showed that our proposed method showed more clearly the scene and the content and more details of the image than the previous methods. We also verified our method and calculated Structural Similarity (SSIM) and Peak Signal-to-Noise Ratio (PSNR) of original images and color pencil drawings with different algorithms on the 7 nature images and the BSDS500 data set.

An analysis on the picture books and extended activities of commercialized reading programs for young children

본 연구는 상품화된 유아 독서 프로그램 그림책의 특성을 분석하여, 유아 독서 프로그램의 질적 향상과 유아에게 적합한 좋은 그림책을 선정하고 개발하는데 필요한 기초 자료를 제공하는데 목적이 있다. 이를 위하여 두 개의 상품화된 유아 독서프로그램에서 활용하는 88권의 그림책과 22권의 확장활동지에 제시된 연계활동을 분석하였다. 그 결과, 그림책의 글 작가와 그림 작가는 국내와 북미, 유럽 작가의 작품이 대부분이었고 그림책의 장르는 픽션 중 사실주의 그림책이 가장 많았으며 운문 그림책은 없었다. 그림책의 표현양식은 만화적 표현을 주로 사용했으며 그림책의 문학성, 예술성, 교육성 측면에서 평가한 점수는 평균보다 낮은 수준으로 나타났다. 연계활동은 의사소통영역 활동이 가장 많았다. 이에 상품화된 프로그램의 그림책의 질적 향상과 유아에게 적합한 좋은 그림책을 선정하는데 필요한 기초 자료와 정보의 근거를 제공하는데 연구의 의의를 둔다.The purpose of this study was to examine the picture books of commercialized reading programs for young children which were extendedly used by child-care centers in the capital area and then provide basic data and information. For this purpose, 88 picture books and 22 workbooks were analysed. The results are as follows: First, most of authors of texts and pictures of picture books of A and B Publishers consisted of Koreans, North Americans and Europeans. Second, realism picture books were the most numerous genre, on the other hand, they did not use verse-type picture books at all. Third, cartoon style expressions were the most numerous. Fourth, regarding the literary/artistic/educational values of picture books were below average, and they had no appropriate literary/artistic/educational values for the developmental level of young children. Fifth, the area of communication were the most numerous in extended activities of workbooks.

Method of the Colombian painter (Fernando Botero) In the embodiment of the Abu Ghraib prison events

Torture and human rights abuses in the treatment of Iraqi prisoners by the US occupation forces In Abu Ghraib prison, These acts have become an international icon representing immoral actions, Colombian artist (Fernando Botero) has performed more than 50 works of painting, The artist embodied These bad prison events in his style, which expresses ridicule and mockery by drawing people with cartoon style & the shapes are so fat and flabby buttocks chunky and huge, And full faces with Precise details, In a way that brought the characters out of their realism and increased their obesity. The researcher relied on a collection of reports, most notably the (Taguba) report, the name of the prison site commander who appeared to have filed numerous complaints about (Abu Ghraib). Five samples were selected, Selectively, From the works of the artist (Abu Ghraib series),& The adoption of the descriptive and analytical approach In analysis the works, It has reached a set of results, The most prominent, Botero expressed his disgust at that incident, Trying to repeat ,The ugliness of what happened to mind, Using (obesity), As a distorted and shocking expression, For the recipient, About what happened in Abu Ghraib prison, And revolution ,Againstreality.

Visual Art in Motion Comic Sirup Manis Sofia

Helping each other is one of moral values that are important to introduce to children because humans are social creatures. To convey this message, required a media that suite children to attract their interest, which is motion comic. To make motion comic become more attractive, the visual style that used is modernist cartoon style that popular in animation and illustrations of the 1950s.&#x0D; Keywords: helping, motion comic, modernist