Character Animation Research Articles

Stylized Representation of Guangzhou Cantonese Opera Characters in Animation within the Context of Cultural and Tourism Integration

Under the broad background of cultural and tourism integration, Guangzhou Cantonese Opera, as a vital part of Chinese traditional culture, has become crucial in its inheritance and innovation. This paper aims to explore the stylized representation and innovative application of Guangzhou Cantonese Opera characters in animation within the context of cultural and tourism integration. By reviewing the history and current status of Cantonese Opera culture, and analyzing the concept and trends of cultural and tourism integration, the unique role of Cantonese Opera in this integration is examined. The study focuses on the definition of stylized representation and its unique position in Cantonese Opera art, and explores strategies for incorporating traditional stylized features into the design of Guangzhou Cantonese Opera animated characters. Additionally, this paper proposes strategies for combining tradition and modernity, developing and promoting cultural and tourism products, and innovative approaches to education and inheritance, providing new perspectives for the inheritance and development of Cantonese Opera culture in modern society.

Animated Character Tool for Improved Communication with Elderly People with Mild Cognitive Impairment

Owing to the increase in the population of elderly people, the number of people suffering from mild cognitive impairment is increasing in several countries. Furthermore, family members of people with mild cognitive impairment, such as reduced function of memory, reasoning, and decision-making, undergo severe stress owing to difficulties in communicating with them. There are, however, few existing technologies to support learning this type of communication to reduce this stress. This study proposes a tool wherein an animated character resembles the behavior of elderly people with mild cognitive impairment in different scenarios to teach how to communicate with them. Fundamental experiments were conducted to confirm the validity of the proposal tool, and results showed that the tool successfully helped users learn how to communicate with elderly people with mild cognitive impairment. Furthermore, we demonstrated the advantages of using an animated character to depict the behavior of people with mild cognitive impairment. We believe the proposed tool enables the imagination of difficult situations and the understanding of communication with the elderly.

3D Character Animation and Asset Generation Using Deep Learning

Besides video content, a significant part of entertainment is represented by computer games and animations such as cartoons. Creating such entertainment is based on two fundamental steps: asset generation and character animation. The main problem stems from its repetitive nature and the needed amounts of concentration and skill. The latest advances in deep learning and generative techniques have provided a set of powerful tools which can be used to alleviate these problems by facilitating the tasks of artists and engineers and providing a better workflow. In this work we explore practical solutions for facilitating and hastening the creative process: character animation and asset generation. In character animation, the task is to either move the joints of a subject manually or to correct the noisy data coming out of motion capture. The main difficulties of these tasks are their repetitive nature and the needed amounts of concentration and skill. For the animation case, we propose two decoder-only transformer based solutions, inspired by the current success of GPT. The first, AnimGPT, targets the original animation workflow by predicting the next pose of an animation based on a set of previous poses, while the second, DenoiseAnimGPT, tackles the motion capture case by predicting the clean current pose based on all previous poses and the current noisy pose. Both models obtained good performances on the CMU motion dataset, with the generated results being imperceptible to the untrained human eye. Quantitative evaluation was performed using mean absolute error between the ground truth motion vectors and the predicted motion vector. For both networks AnimGPT and DenoiseAnimGPT errors were 0.345, respectively 0.2513 (for 50 frames) that indicates better performances compared with other solutions. For asset generation, diffusion models were used. Using image generation and outpainting, we created a method that generates good backgrounds by combining the idea of text conditioned generation and text conditioned image editing. A time coherent algorithm that creates animated effects for characters was obtained.

The Environmental Function of Animal Characters Across Different Literary Genres

This article explores the remarkable versatility of animal images and characters through their function in literature. The representation of animals in literature has emerged as one of the powerful tools for promoting environmental awareness and advocacy. Across diverse literary genres, the use of animal imagery and characters serves a multitude of functions in catalyzing ecological consciousness. In lyrical nature writing, vivid descriptions of animals and their habitats evoke emotional resonance, inviting readers to appreciate the fragility and resilience of ecosystems. Allegorical narratives, meanwhile, employ animal protagonists to challenge societal norms and expose environmental injustices through metaphorical storytelling. Even in children's literature, charming portrayals of animal characters serve as accessible gateways for young readers to the natural world.

Resolving Collisions in Dense 3D Crowd Animations

We propose a novel contact-aware method to synthesize highly-dense 3D crowds of animated characters. Existing methods animate crowds by, first, computing the 2D global motion approximating subjects as 2D particles and, then, introducing individual character motions without considering their surroundings. This creates the illusion of a 3D crowd, but, with density, characters frequently intersect each other since character-to-character contact is not modeled. We tackle this issue and propose a general method that considers any crowd animation and resolves existing residual collisions. To this end, we take a physics-based approach to model contacts between articulated characters. This enables the real-time synthesis of 3D high-density crowds with dozens of individuals that do not intersect each other, producing an unprecedented level of physical correctness in animations. Under the hood, we model each individual using a parametric human body incorporating a set of 3D proxies to approximate their volume. We then build a large system of articulated rigid bodies, and use an efficient physics-based approach to solve for individual body poses that do not collide with each other while maintaining the overall motion of the crowd. We first validate our approach objectively and quantitatively. We then explore relations between physical correctness and perceived realism based on an extensive user study that evaluates the relevance of solving contacts in dense crowds. Results demonstrate that our approach outperforms existing methods for crowd animation in terms of geometric accuracy and overall realism.

Animal’s Gaze in Sinha’s Animal’s People

The article critically studies Indra Sinha's Animal’s People by critiquing Animal, a deformed young man born in the aftermath of the Bhopal disaster. Narrated by Animal himself via tapes transcribed by an Australian journalist, the novel explores themes of animality, identity, and representation. The article draws on a variety of scholarly perspectives, including ecocriticism, postcolonial criticism, posthumanism, and others to uncover the complexities of Animal's character. Drawing on the insights of Julietta Singh, Justin Omar Johnston and Andrew Mahlstedt, among many other scholars, the paper critiques common interpretations of Animal as the voice of the oppressed and offers a new perspective on his character. The paper argues that Animal's voyeuristic gaze is not compatible with typical animal behavior, but rather affirms Animal’s compromised morality as a deformed human being. Despite his efforts to establish his animality, Animal's actions betray macho human tendencies and challenge the idea that he is the appropriate figure to represent animals and ecology at large.

Hearing Animals’ Stories: Interspecies Bond in Sanjeev Upreti’s Hansa

This paper analyzes Sanjeev Upreti’s Hansa (Duck), published in 2076 BS (2019 AD) from the perspective of Literary Animal Studies with a major objective of unveiling the author’s awareness of the exigency of an equitable and sustainable animal-human bond in the contemporary Anthropocene. The novel unfolds twin narratives in which one is a human protagonist and another a duck. In both narratives, stories of animals are foregrounded. Animal characters narrate their own stories that consist of their grievances of cruelties and indifference they face at the hand of humans. The human protagonist hears and understand these stories. It raises a question: why does he hear their stories? After analyzing the textual evidence through the theoretical perspective of Literary Animal Studies by focusing on Susan McHugh’s concept of animal narrative agency, the paper finds the answer that the human protagonist hears the animals’ stories because they underscore narrative agency. Unlike conventional roles of animals as metaphors and symbols for the making of human identity, these animals play an active role in resisting human exploitation against them. Finally, the paper claims that by offering narrative agency to animal characters, the author highlights the need of building an entangled interspecies bond among human and nonhuman animals. With this, the study expects to be useful for those readers and researchers interested in the field of Literary Animal Studies.

A Review on Modern Techniques in 3D Character Animation

3D character animation is a pivotal aspect of digital graphics, essential for various applications such as films, games, and simulations. This review paper explores advancements in character animation techniques, including linear blend skinning, dual quaternion skinning, and physics-based approaches. Emphasis is placed on recent innovations aimed at improving the realism and computational efficiency of character deformations, especially non-rigid transformations. By examining key methodologies and their applications, this paper provides a comprehensive overview of the current state and future directions in 3D character animation

Machine Learning Approaches for 3D Motion Synthesis and Musculoskeletal Dynamics Estimation: A Survey.

The inference of 3D motion and dynamics of the human musculoskeletal system has traditionally been solved using physics-based methods that exploit physical parameters to provide realistic simulations. Yet, such methods suffer from computational complexity and reduced stability, hindering their use in computer graphics applications that require real-time performance. With the recent explosion of data capture (mocap, video) machine learning (ML) has started to become popular as it is able to create surrogate models harnessing the huge amount of data stemming from various sources, minimizing computational time (instead of resource usage), and most importantly, approximate real-time solutions. The main purpose of this paper is to provide a review and classification of the most recent works regarding motion prediction, motion synthesis as well as musculoskeletal dynamics estimation problems using ML techniques, in order to offer sufficient insight into the state-of-the-art and draw new research directions. While the study of motion may appear distinct to musculoskeletal dynamics, these application domains provide jointly the link for more natural computer graphics character animation, since ML-based musculoskeletal dynamics estimation enables modeling of more long-term, temporally evolving, ergonomic effects, while offering automated and fast solutions. Overall, our review offers an in-depth presentation and classification of ML applications in human motion analysis, unlike previous survey articles focusing on specific aspects of motion prediction.

Research on the Influence of Japanese Anime on Chinese College Students' Consumption Habits in Haikyu

With the popularity of Japanese anime in China, the behavior of Chinese college students consuming Japanese anime derivatives has received widespread attention. In the existing research, there is a lack of discussion on the consumption of anime animation cultural products by Chinese college students. Therefore, this study takes Haikyu as an example to analyze the impact of Japanese action anime (with friendship, effort, and desire to win) on the consumption habits of Chinese college students. Analysis shows that the emotional resonance between such Japanese action anime and Chinese college students, as well as the love of Chinese college students for anime characters, affects the demand psychology, purchase motivation, and consumption willingness of college students in terms of consumption habits. Meanwhile, Chinese college students are becoming more rational in their consumption of peripheral products from Japanese anime. Based on this, this study provides a detailed explanation of the two factors that influence the consumption habits of Chinese college students, including themes such as friendship, youth, and dreams in Japanese anime, as well as their love for characters portrayed in anime.

Bibliometric Analysis of a Comprehensive of Culture and Symbol in Character Animation during (2004–2024)

The analysis of academic research on animated characters in the animation industry effectively summarises the current state of scholarly research on animated characters through a variety of software tools such as CiteSpace, VOS viewer, HistCite, and Bibliometrix analysis, and visually charts and formulates this data. Through study and research, it that the United States is (278) the most prolific country, and the United States has the highest intermediary centrality, as well as the most Centre National de la Recherche Scientifique (CNRS) and PEOPLES R CHINA are the most cited organizations and Countries/Regions with the highest intermediary centrality and Countries/Regions with the highest citation explosiveness, respectively. This study also suggests possible challenges and future directions in character design for animated characters.

S3: Speech, Script and Scene driven Head and Eye Animation

We present S 3 , a novel approach to generating expressive, animator-centric 3D head and eye animation of characters in conversation. Given speech audio, a Directorial script and a cinematographic 3D scene as input, we automatically output the animated 3D rotation of each character's head and eyes. S 3 distills animation and psycho-linguistic insights into a novel modular framework for conversational gaze capturing: audio-driven rhythmic head motion; narrative script-driven emblematic head and eye gestures; and gaze trajectories computed from audio-driven gaze focus/aversion and 3D visual scene salience. Our evaluation is four-fold: we quantitatively validate our algorithm against ground truth data and baseline alternatives; we conduct a perceptual study showing our results to compare favourably to prior art; we present examples of animator control and critique of S 3 output; and present a large number of compelling and varied animations of conversational gaze.

Categorical Codebook Matching for Embodied Character Controllers

Translating motions from a real user onto a virtual embodied avatar is a key challenge for character animation in the metaverse. In this work, we present a novel generative framework that enables mapping from a set of sparse sensor signals to a full body avatar motion in real-time while faithfully preserving the motion context of the user. In contrast to existing techniques that require training a motion prior and its mapping from control to motion separately, our framework is able to learn the motion manifold as well as how to sample from it at the same time in an end-to-end manner. To achieve that, we introduce a technique called codebook matching which matches the probability distribution between two categorical codebooks for the inputs and outputs for synthesizing the character motions. We demonstrate this technique can successfully handle ambiguity in motion generation and produce high quality character controllers from unstructured motion capture data. Our method is especially useful for interactive applications like virtual reality or video games where high accuracy and responsiveness are needed.

CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization

BNRist, Department of Computer Science and Technology, Tsinghua University, China In the field of digital content creation, generating high-quality 3D characters from single images is challenging, especially given the complexities of various body poses and the issues of self-occlusion and pose ambiguity. In this paper, we present CharacterGen, a framework developed to efficiently generate 3D characters. CharacterGen introduces a streamlined generation pipeline along with an image-conditioned multi-view diffusion model. This model effectively calibrates input poses to a canonical form while retaining key attributes of the input image, thereby addressing the challenges posed by diverse poses. A transformer-based, generalizable sparse-view reconstruction model is the other core component of our approach, facilitating the creation of detailed 3D models from multi-view images. We also adopt a texture-back-projection strategy to produce high-quality texture maps. Additionally, we have curated a dataset of anime characters, rendered in multiple poses and views, to train and evaluate our model. Our approach has been thoroughly evaluated through quantitative and qualitative experiments, showing its proficiency in generating 3D characters with high-quality shapes and textures, ready for downstream applications such as rigging and animation.

Narrative Analysis of Pañcatantra

Pañcatantra is a widely spread and popular text in world literature. Pañcatantra is available in more than 200 versions in over 50 languages, more than 35 of which are non-Indian languages. Pañcatantra though known as a didactic fable its primary intention is to give the lessons of polity, diplomacy and worldly wisdom. This is well understood when the word tantra is decoded using tools of narrative analysis. ‘Box in box tale’ is a remarkable feature of Sanskrit literature. Pañcatantra skillfully uses this to convey the import but at the same time ‘box in box pattern’ is used in such a manner that stories are bound with each other as well as loose. Due to this, they have become popular in an independent manner as well in different languages. The employment of animal characters in the story is yet another remarkable feature of Pañcatantra which has helped to convey the message effectively. The frame story of Viṣṇuśarman is yet another narrative which is attached to Pañcatantra. It’s worth thinking about whether this story is real or fictitious like other stories of Pañcatantra. This paper is an attempt to analyze the narrative features of Pañcatantra to understand the secret of its popularity.

Machine Learning-Based Human Movements Mimicking System for Animation and Virtual Reality

A trend, which can be noticed over the last several years, is the increasing interest to the machine learning methods in the animation and virtual reality (VR) industries to process the human motion data. The present abstract studies the possible contribution of human like machine learning simulations on human motions, which aim to improve animation and motion synthesis personalization. In this research, we propose a novel framework that utilizes camera-captured human motion data. This technique, which takes advantage of comes of motion data to simulate these animated characters movements in real time, will allow animators to create more creature-like animated figures with subtle actions as seen in real life. Additionally, in virtual reality, it links users’ movements with their avatars so the whole interaction is more engaging and realistic.

Integrative redescription of the Xerobiotus euxinus Pilato, Kiosya, Lisi, Inshina & Biserov, 2011 (Tardigrada: Eutardigrada: Macrobiotidae) population from Ukraine

Using integrative taxonomy, we redescribe an eutardigrade Xerobiotus euxinus Pilato et al. 2011 based on material from the type locality and additional population from the Black Sea Biosphere Reserve in the south of Ukraine. Integrative redescription is based on morphological and morphometric data of animals and eggs from both phase contrast light microscopy (PCM), as well as, from scanning electron microscopy (SEM), and four DNA markers, three nuclear (18S rRNA, 28S rRNA, ITS-2) and one mitochondrial (COI). Originally, the species was described solely based on adults’ morphology. The uncorrected genetic distances indicated that X. euxinus is the most similar to X. gretae with a p-distance value of COI fragment. Morphologically, X. euxinus differs from all Xerobiotus taxa mainly by the shape of claws on legs IV, but also by some other morphological and morphometrical characters of eggs and animals.

Appearance-Preserved Portrait-to-Anime Translation via Proxy-Guided Domain Adaptation.

Converting a human portrait to anime style is a desirable but challenging problem. Existing methods fail to resolve this problem due to the large inherent gap between two domains that cannot be overcome by a simple direct mapping. For this reason, these methods struggle to preserve the appearance features in the original photo. In this article, we discover an intermediate domain, the coser portrait (portraits of humans costuming as anime characters), that helps bridge this gap. It alleviates the learning ambiguity and loosens the mapping difficulty in a progressive manner. Specifically, we start from learning the mapping between coser and anime portraits, and present a proxy-guided domain adaptation learning scheme with three progressive adaptation stages to shift the initial model to the human portrait domain. In this way, our model can generate visually pleasant anime portraits with well-preserved appearances given the human portrait. Our model adopts a disentangled design by breaking down the translation problem into two specific subtasks of face deformation and portrait stylization. This further elevates the generation quality. Extensive experimental results show that our model can achieve visually compelling translation with better appearance preservation and perform favorably against the existing methods both qualitatively and quantitatively. Our code and datasets are available at https://github.com/NeverGiveU/PDA-Translation.

StyleVR: Stylizing Character Animations With Normalizing Flows.

The significance of artistry in creating animated virtual characters is widely acknowledged, and motion style is a crucial element in this process. There has been a long-standing interest in stylizing character animations with style transfer methods. However, this kind of models can only deal with short-term motions and yield deterministic outputs. To address this issue, we propose a generative model based on normalizing flows for stylizing long and aperiodic animations in the VR scene. Our approach breaks down this task into two sub-problems: motion style transfer and stylized motion generation, both formulated as the instances of conditional normalizing flows with multi-class latent space. Specifically, we encode high-frequency style features into the latent space for varied results and control the generation process with style-content labels for disentangled edits of style and content. We have developed a prototype, StyleVR, in Unity, which allows casual users to apply our method in VR. Through qualitative and quantitative comparisons, we demonstrate that our system outperforms other methods in terms of style transfer as well as stochastic stylized motion generation.

Gender stereotypes regarding power and niceness in Japanese children.

Belief in gendered social power imbalance (i.e. males are more powerful than females) leads to undesirable gender disparities, but little is known about the developmental origins of this belief, especially in Eastern cultures. We investigated the development onset of this belief by focusing on 4-7-year-old Japanese children while considering another belief (females are nicer than males) for comparison. In the dyadic context tasks, children saw pairs of animated characters depicting powerful-powerless or kind-unkind postures and judged the characters' gender (boy or girl). Results suggested both 'nice = female' and 'powerful = female' gender stereotypes in children. In the collective context tasks, children were presented with stories in occupational contexts, including multiple unspecified people and verbal cues, describing more explicitly the powerful and nice traits of the protagonists. The results replicated the 'nice = female' gender stereotype. Moreover, early 'powerful = male' gender stereotypes were seen in 6-year-old boys but not among girls in general. These findings demonstrate that Japanese children's beliefs regarding gender differences in power vary depending on the context in which male-female interactions are presented. Additionally, the study reveals that signs of the 'powerful = male' social power gender stereotype emerge around the ageof 6.