Digital Humans Research Articles

Effects of meta-human characteristics on user acceptance: from the perspective of uncanny valley theory

ABSTRACT Despite the potential of meta-humans in the virtual space, research on how consumers react to meta-humans is scarce. This study investigates the effects of meta-human characteristics on user acceptance. 280 responses from the online survey were analysed using structural equation modelling. Findings revealed that meta-humans outshine digital humans in terms of performance and user acceptance. Users encountering digital humans are affected by the uncanny valley in terms of appearance and function. However, users encountering meta-humans are affected only in terms of function. Social presence and perceived novelty are additional factors affecting user acceptance. Theoretically, this study contributes to the literature by confirming the existence of the uncanny valley effect in meta-humans and by expanding human likeness to appearance and behaviour. Although meta-humans have surpassed the uncanny valley in appearance, they still lack familiarity in terms of behaviour. Practically, meta-humans and meta-human modelling tools have been found to surpass existing digital human technology both in performance and user acceptance. However, behavioural human likeness must continue to be developed in order to further increase user acceptance. Furthermore, familiarity does not directly affect user acceptance but mediates satisfaction. As user acceptance follows satisfaction, marketers should investigate user satisfaction rather than improving human likeness.

MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators

Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Visit our webpage at https://qiqiapink.github.io/MotionGPT/.

Fashion intelligence in the Metaverse: promise and future prospects

With the development of artificial intelligence (AI) and the constraints on offline activities imposed due to the sudden outbreak of the COVID epidemic, the Metaverse has recently attracted significant research attention from both academia and industrial practitioners. Fashion, as an expression of a consumer’s aesthetics and personality, has enormous economic potential in both the real world and the Metaverse. In this research, we provide a comprehensive survey of two of the most important components of fashion in the Metaverse: virtual digital humans, and tasks related to fashion items. We survey state-of-the-art articles from 2007 to the present and provide a new taxonomy of extant research topics based on these articles. We also highlight the applications of these topics in the Metaverse from the perspectives of designers and consumers. Finally, we describe possible scenes involving fashion in the Metaverse. The current challenges and open issues related to the fashion industry in the Metaverse are also discussed in order to provide guidance for fashion practitioners, and to shed some light on the future development of fashion AI in the Metaverse.

Exploiting global and instance-level perceived feature relationship matrices for 3D face reconstruction and dense alignment

3D face reconstruction and dense alignment play a key role in digital humans. Learning-based approaches have been developed by employing cascaded convolutional neural networks for feature extraction and spatial-semantic relationship construction. However, these networks often struggle with accurately capturing the complex relationships among various facial components and attributes, particularly in unconstrained environments. Furthermore, the mappings modeled by convolutional weights are at low levels, which are usually implicit and local, and lack global discrimination. In this paper, we propose a global and instance-level perceived relationship matrices-based network (PRMNet) to recover high-fidelity 3D faces and perform accurate dense alignment in unconstrained environments. Specifically, a Key Information Extraction Module (KIEM) extracts crucial features from global and local feature banks. This reduces reasoning costs while maintaining high perceptual quality. Learnable global and instance-level perceived feature relationship matrices are then integrated into the Feature Relationship Reasoning Module (FRRM). This calibration combines key information from both the global macroscopic and sample-specific microscopic views, allowing accurate construction of spatial-semantic relationships to harvest both global discrimination and local relevance. Finally, we introduce a Spatial Reasoning and Guidance Module (SRGM), designed to recalibrate the joint weight responses of feature extraction and its enhancement paths using various attention mechanisms, thereby further enhancing global discrimination ability. Extensive quantitative and qualitative experiments on the benchmark datasets show that our PRMNet outperforms the state-of-the-art. Codes and all resources will be publicly available at https://github.com/Ray-tju/PRMNet.

The Virtual and Realistic Journey of Digital Human: An Assemblage of Urban Communication

Artificial intelligence technology provides conditions for the development, improvement, and promotion of digital humans. As a hot spot in current social media, digital humans have formed a continuously changing but relatively stable urban assemblage with elements such as urban image architecture, urban cultural communication, and urban image in social platforms. From the assemblage perspective, this paper analyzes the content of virtual people and urban culture communication in social media though assemblage ethnography. These materials show that in the social environment of rapid development and change of new technology, active use of new technology and new media platforms is conducive to the dissemination and development of traditional culture, while increasing the attraction to young audiences and building a dynamic urban imagination. It also emphasizes the importance of paying attention to the interaction between humans and non-humans and breaking the boundary between virtual and reality in the ever-changing social environment.

Digital Humans to Combat Loneliness and Social Isolation: Ethics Concerns and Policy Recommendations.

Social isolation and loneliness are growing concerns around the globe that put people at increased risk of disease and early death. One much-touted approach to addressing them is deploying artificially intelligent agents to serve as companions for socially isolated and lonely people. Focusing on digital humans, we consider evidence and ethical arguments for and against this approach. We set forth and defend public health policies that respond to concerns about replacing humans, establishing inferior relationships, algorithmic bias, distributive justice, and data privacy.

A Coeditors' Note

AbstractThe January‐February 2024 issue of the Hastings Center Report includes two sets of pieces concerning brain health. One is a special report on ethical challenges that emerge at various points in the care of people facing dementia. The other set launches the journal's Neuroscience and Society series. An At Law essay provides a framework for challenging discriminatory practices related to the use of algorithms generated by electronic prescription drug monitoring programs in health care. The issue also contains policy recommendations for the use of companion digital humans to address social isolation and loneliness, guidance for the rollout of vaccine delivery technologies, and a call for ethical investigation of data infrastructure.

디지털휴먼의 평가지표에 관한 연구

In the 4th industrial revolution, this study seeks to focus on digital human technology among digital technologies. This technology has grown in many fields such as medicine, education, finance, and entertainment, but it shows limitations such as information security, job instability, and digital divide. Accordingly, this study aims to explore continuous innovation and development based on users' emotional experiences in the field of digital human services and study design principles based on emotional recognition. The focus of the study was to use methods such as exploratory factor analysis, ANOVA analysis, and reliability analysis based on the understanding of design evaluation indicators related to digital humans. Through this method, we aim to identify design evaluation indicators that have a significant impact on user experience and ensure the reliability and stability of these indicators. The need for this study is to provide important references and guidelines for digital human design, helping designers better meet users' emotional and actual needs. Additionally, the research results provide a basis for evaluating the usability of digital human emotion design and have important implications for this field. Through this study, we gained a clear understanding of the needs and preferences of users of various age groups and revealed how they respond to digital human emotional design. In particular, adult users have higher expectations and demands in terms of digital human emotional design and pay more attention to intuitiveness, feedback, consistency, discoverability, flexibility, error tolerance, user engagement, personalization and emotional feedback, storytelling and adaptability. In this respect, the requirements of elderly users are relatively low. I'm leaning. This provides important insights for determining the direction of future digital human design. We hope that the results of this study will contribute to improving user experience by developing digital human design in a more emotional direction.

Examining the Impact of Digital Human Gaze Expressions on Engagement Induction.

With advancements in technology, digital humans are becoming increasingly sophisticated, with their application scope widening to include interactions with real people. However, research on expressions that facilitate natural engagement in interactions between real people and digital humans is scarce. With this study, we aimed to examine the differences in user engagement as measured by subjective evaluations, eye tracking, and electroencephalogram (EEG) responses relative to different gaze expressions in various conversational contexts. Conversational situations were categorized as face-to-face, face-to-video, and digital human interactions, with gaze expressions segmented into eye contact and gaze avoidance. Story stimuli incorporating twelve sentences verified to elicit positive and negative emotional responses were employed in the experiments after validation. A total of 45 participants (31 females and 14 males) underwent stimulation through positive and negative stories while exhibiting eye contact or gaze avoidance under each of the three conversational conditions. Engagement was assessed using subjective evaluation metrics in conjunction with measures of the subjects' gaze and brainwave activity. The findings revealed engagement disparities between the face-to-face and digital-human conversation conditions. Notably, only positive stimuli elicited variations in engagement based on gaze expression across different conversation conditions. Gaze analysis corroborated the engagement differences, aligning with prior research on social sensitivity, but only in response to positive stimuli. This research departs from traditional studies of un-natural interactions with digital humans, focusing instead on interactions with digital humans designed to mimic the appearance of real humans. This study demonstrates the potential for gaze expression to induce engagement, regardless of the human or digital nature of the conversational dyads.

Revisiting the elaboration likelihood model in the context of a virtual influencer: A comparison between high‐ and low‐involvement products

AbstractWhile existing research on the elaboration likelihood model (ELM) has primarily focused on human influencers, the literature on virtual influencers (also known as digital humans or AI influencers) remains limited. To address this research gap, this study investigates the factors influencing consumer attitudes toward ads promoted by virtual influencers. Extending the ELM framework, we examine perceived expertise and attractiveness as antecedents, and explore consumer online‐to‐offline dynamics as consequences. Using a multigroup structural equation model, the study compares high‐ and low‐involvement product ads by analyzing questionnaires (n = 406). A novelty lies in our findings that, contrary to existing ELM research, perceived attractiveness significantly influences attitudes toward the ads across both high‐ and low‐involvement levels. We attribute this result to a shift of consumer attention towards virtual influencers, driven by their attention‐grabbing aesthetic appeals. Our study extends the ELM framework and contributes to the literature on digital marketing, advertising, and human‐computer interaction.

From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans

Great progress has been made in estimating 3D human pose and shape from images and video by training neural networks to directly regress the parameters of parametric human models like SMPL. However, existing body models have simplified kinematic structures that do not correspond to the true joint locations and articulations in the human skeletal system, limiting their potential use in biomechanics. On the other hand, methods for estimating biomechanically accurate skeletal motion typically rely on complex motion capture systems and expensive optimization methods. What is needed is a parametric 3D human model with a biomechanically accurate skeletal structure that can be easily posed. To that end, we develop SKEL, which re-rigs the SMPL body model with a biomechanics skeleton. To enable this, we need training data of skeletons inside SMPL meshes in diverse poses. We build such a dataset by optimizing biomechanically accurate skeletons inside SMPL meshes from AMASS sequences. We then learn a regressor from SMPL mesh vertices to the optimized joint locations and bone rotations. Finally, we re-parametrize the SMPL mesh with the new kinematic parameters. The resulting SKEL model is animatable like SMPL but with fewer, and biomechanically-realistic, degrees of freedom. We show that SKEL has more biomechanically accurate joint locations than SMPL, and the bones fit inside the body surface better than previous methods. By fitting SKEL to SMPL meshes we are able to "upgrade" existing human pose and shape datasets to include biomechanical parameters. SKEL provides a new tool to enable biomechanics in the wild, while also providing vision and graphics researchers with a better constrained and more realistic model of human articulation. The model, code, and data are available for research at https://skel.is.tue.mpg.de.

Homo Digitals как продукт цифровизации

Digitalization, which has penetrated all spheres of human activity, is purposefully creating a digital human being, who will be existing simultaneously and inseparably in the ordinary and digital worlds with the help of augmented and virtual reality technologies. Digital human beings can have a chip implanted in the brain to be in constant communication with the digital environment; moreover, they can exist in a completely digitized form in a digital universe. The key issue that requires philosophical analysis is the expediency of creating a digital human being. The main question to be answered is “When should we stop?”. Undoubtedly, digitalization is a boon for the development of society, and many of its processes are firmly rooted in social practice. Is it necessary to change the status of this process from instrumental (auxiliary) to ontological (essential)? Experiments on the digitization of human consciousness, creation of a metauniverse, and such projects as Neuronet and University 4.0, as well as Industry 4.0 actively contribute to changing the status of digital technologies from human assistant to essential component of humans. At the stage of developing a digital model of society, it is still difficult to predict all its negative aspects. However, based on the existing risks in the field of digitalization, it can be assumed that this innovation initially poses a threat to humanity. The most likely risks that digital humans will face include depersonalization and high exposure to suggestion as well as loss of personal space and economic independence. In this regard, one should be critical of total digitalization and stop its advancement in time.

Literary Theory and Cultural Practice of “Metaverse” in China

ABSTRACT The concept of the “metaverse” has triggered extensive discussions across various fields in China, leading to a significant increase in the number of articles related to this topic in 2022. In general, Chinese scholars in the humanities exhibit two divergent inclinations when it comes to the concept of “metaverse.” Some tend to metaphysicise or de-metaphysicise it, while others aim to contextualise it through a Chinese lens or decontextualise it from the perspective of the Chinese language and culture (i.e. Chinese-style understanding/de-Chinese-contextualisation). Given that the “metaverse” is a completely new concept pointing to the future, Chinese scholars are limited to utilising existing theoretical resources to analyze artistic issues related to the “metaverse.” They primarily focus on three aspects: interaction and immersion technologies, body–subject relations, and narrative. However, their analyses often suffer from the problem of misusing literary theory, akin to putting old wine in new bottles. Currently, “metaverse” creative cultural projects in China mainly centre on digital collectibles, virtual digital humans, and immersive experiences in tourism. However, these artifacts encounter intense challenges, including the inefficient utilisation of digital cultural capital, the rigid replication of content, an overemphasis on simulacra, and a lack of emphasis on conveying cultural values.

How Digital Humans Help Libraries Promote Reading

ABSTRACTThis study investigated how digital humans can help libraries promote reading. This study recruited 103 participants for a user experiment to explore their satisfaction with reading promotional videos using digital humans. At the same time, the effect of using digital humans in library reading promotion was analyzed from the perspective of whether users are willing to share and interact. Research has found that user satisfaction with them is not high due to digital human presence in their voice and intonation. But users are more interested in using anime digital human videos. This discovery can help libraries better carry out reading promotion and digital services.

A survey on generative 3D digital humans based on neural networks: representation, rendering, and learning

A survey on generative 3D digital humans based on neural networks: representation, rendering, and learning

Design and development of digital humans in virtual exhibition space

Design and development of digital humans in virtual exhibition space

4DHumanOutfit: A multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements

We present a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions. The dataset contains different actors wearing different outfits while performing different motions in each outfit. It samples the space of 4D human motion along 3 axes with identity, outfit and motion, therefore providing a cube of data where each identity is represented by a planar slice of the cube with all outfits and for all motions. The dataset has numerous potential applications for the processing and creation of digital humans including augmented reality, avatar creation and virtual try on. 4DHumanOutfit is released for research purposes at https://kinovis.inria.fr/4dhumanoutfit/. In addition to image data and 4D reconstructions, the dataset includes reference solutions for each axis. We present independent baselines along each axis that demonstrate the value of these reference solutions for evaluation tasks.

A no-reference quality assessment metric for dynamic 3D digital human

Dynamic Digital Humans (DDHs) refer to 3D digital models that are animated using predefined motions. However, these models are susceptible to noise and shift distortions during the generation process, as well as compression distortions during transmission and communication. It is crucial to evaluate the perceptual quality of DDHs in order to address these challenges. Typically, DDHs are presented as 2D rendered animation videos, making it reasonable to adapt video quality assessment (VQA) methods for DDH quality assessment (DDH-QA) tasks. Nevertheless, VQA methods heavily rely on viewpoints and exhibit limited sensitivity to geometry-based distortions. Consequently, this paper introduces a novel no-reference (NR) quality assessment metric specifically tailored for the DDH-QA challenge. In this proposed method, the geometry characteristics of DDHs are characterized by computing statistical parameters estimated from the distributions of their geometry attributes. Additionally, spatial and temporal features are extracted from the rendered videos. Subsequently, all relevant features are integrated and regressed into quality values. Through comprehensive experiments conducted on the DDH-QA database, the results demonstrate that the proposed method achieves state-of-the-art performance in assessing the quality of DDHs.

Augmented digital human vs. human agents in storytelling marketing: Exploratory electroencephalography and experimental studies

AbstractAs the fourth industrial revolution unfolds and the use of digital humans becomes more commonplace, understanding digital humans' potential to replace real human interaction or enhance it, particularly in storytelling marketing contexts, is becoming evermore important. To promote interaction and increase the entertainment value of technology‐enhanced storytelling marketing, brands have begun to explore the use of augmented digital humans as storytelling agents. In this article, we examine the effectiveness of leveraging advanced technologies and delivering messages via digital humans in storytelling advertisements. In Study 1, we investigate the effectiveness of narrative transportation on behavioral responses after exposure to an interactive augmented reality mobile advertisement with a digital human storyteller. In Study 2, we compare how consumers respond to augmented digital human versus real human storytelling advertisements after conducting an exploratory neurophysiological electroencephalography study. The findings show that both types of agents promote narrative transportation when the story fits the product well. Moreover, a digital human perceived as more human‐like elicits stronger positive consumer responses, suggesting an effective new approach to storytelling marketing.

Social intimacy and skewed love: A study of the attachment relationship between internet group young users and a digital human

Interactions between human beings and digital humans have become a new network phenomenon, and these relationships have gradually become a topic of research. There is still a lack of sufficient research on whether and what kind of attachment relationship exists in these situations. Based on this problem, in this study, a digital human was designed that was oriented to social software and put into chat groups for interaction and research. A questionnaire survey, case analysis, and netnography analysis were used to collect and examine relevant data. The study found a correlation between the type of attachment of users and the degree of attachment to the digital human. In addition, users who were heavily dependent on the network were more likely to try to complete their attachment with the digital human. Attachment with the digital human was able to calm the users’ emotional intensity. This attachment was considered as close to a skewed desire projection. Through the intermediary of a digital human, Internet users have been better able to fulfill some of their own desires.