{"title":"SSGesture: Multimodal Gesture Generation Framework for Human Animation Synthesis.","authors":"Xinyi Wang, Shiguang Liu, Xu Yang","doi":"10.1109/MCG.2025.3577477","DOIUrl":"https://doi.org/10.1109/MCG.2025.3577477","url":null,"abstract":"<p><p>Technological innovations are reshaping the development of animation production. As virtual characters are increasingly used in animation creation and smart assistants, a key challenge is how to automatically generate dialogue gestures. However, current approaches often overlook a wide range of modalities and their interactions, resulting in gestures that have low contextual variation and noticeable jitter. To address these issues, we propose SSGesture, a novel diffusion-based framework that effectively captures cross-modal associations. Our three-layer attention structure enhances multimodal processing. We propose the first method to automatically resolve style conflicts through interpolation-based gesture style control, while implementing a unified unmarked style prompt structure via the PAAN layer. Our framework is practically applied in the field of intelligent virtual assistants to generate gestures in human animation synthesis and to realize various new applications. Extensive experiments and user studies have demonstrated that our proposed framework, provides substantial assistance in enhancing the efficiency of human animation production.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144250975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ethical Considerations and Implications of Generative AI in Computer Graphics.","authors":"Sudhir K Routray","doi":"10.1109/MCG.2025.3570722","DOIUrl":"https://doi.org/10.1109/MCG.2025.3570722","url":null,"abstract":"<p><p>Generative AI has immense potential to create diverse computer graphics for various applications, but it also raises significant ethical issues. This paper examines the ethical landscape of using generative AI in computer graphics, highlighting key concerns such as the authenticity of generated content, intellectual property rights, and cultural appropriation. Additional ethical challenges include algorithmic bias in graphics generation, representation, privacy, inclusivity, and the impact on human-computer interaction and artistic integrity. The displacement of creative professionals, erosion of trust in visual media, and psychological effects of AI-generated content further complicate the ethical debate. Addressing these issues requires a comprehensive approach that integrates technological innovation with regulatory oversight, ethical education, and collaboration among stakeholders. By carefully considering these ethical dimensions, we can fully leverage generative AI's potential in computer graphics while mitigating its risks.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144082153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"\"Paths in Education\": A Case Study on Integrating Statistical Data and Qualitative Narratives using Data Visualization.","authors":"Paula Lago, Stuart King","doi":"10.1109/MCG.2025.3565890","DOIUrl":"https://doi.org/10.1109/MCG.2025.3565890","url":null,"abstract":"<p><p>This case study explores a novel approach to data visualization that integrates statistical data with qualitative narratives, guided by the principles of data feminism and data humanism. The narrative, titled \"Paths in Education\", focuses on secondary education in Uruguay, a country where almost half of young adults have not completed mandatory education. Through a combination of quantitative analysis and interviews, the narrative is presented on an interactive scrollytelling website. The paper discusses the critical visualization theories that inspired the chosen approach, the methodologies used for data collection and analysis, and the design process. It also discusses how the project relates to data feminism and humanism, as well as some lessons learned.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144058231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Joao Luiz Lagoas de A B, Carlos Eduardo Pedreira, Pedro V Sander, Jing Liao
{"title":"A Two-Stage Unsupervised GAN Approach for Anime-to-Manga Translation.","authors":"Joao Luiz Lagoas de A B, Carlos Eduardo Pedreira, Pedro V Sander, Jing Liao","doi":"10.1109/MCG.2025.3567442","DOIUrl":"https://doi.org/10.1109/MCG.2025.3567442","url":null,"abstract":"<p><p>This project aims to investigate how cartoon and comic images can be better explored within the context of unsupervised image-to-image translation. Specifically, we seek to study the translation of anime illustrations into their manga representations, given a manga book as a reference. Although current state-of-the-art image-to-image translation models can convert images between different domains, existing methods for translating illustrations to manga style are scarce. We propose to exploit the unique characteristics of anime and manga images, allowing for a preliminary output that can support the translation process in two stages. We believe this approach can reduce model complexity while generating high-fidelity outputs. Furthermore, we aim to impose minimal restrictions on the manga target domain, making the translation fully unsupervised. Finally, the proposed framework's output can be used to produce rich datasets composed of colored and synthetic manga images, which would support colorization methods that rely on large amounts of paired training data.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144053777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kiegan Rice, Sydney Bell, Taylor Wing, Heike Hofmann, Nola du Toit
{"title":"Measuring Real-World Understanding of Patterns in Data Graphics.","authors":"Kiegan Rice, Sydney Bell, Taylor Wing, Heike Hofmann, Nola du Toit","doi":"10.1109/MCG.2025.3565834","DOIUrl":"https://doi.org/10.1109/MCG.2025.3565834","url":null,"abstract":"<p><p>Presenting data visually is a cornerstone of effective science communication. While prior studies have investigated humans' ability to effectively perceive values in charts, fewer have focused on the translation of perceived values to real-world conclusions. Those that do focus on real-world understanding often utilize convenience samples or focus on very simple graphic formats, resulting in an incomplete understanding of how viewers translate data graphics into meaningful conclusions. We utilize a probability-based sample of over 3,000 participants in the U.S. to test user understanding of three chart types and find that both educational attainment and age play a role in ability to interpret data graphics. Our work demonstrates a need for further study on how chart comprehension and comfort with drawing real-world conclusions differs across demographic groups and commonly-used chart types. Additionally, this work highlights that complex charts can be inaccessible to viewers who lack confidence in reading a chart.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144058785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Georgios Pappas, Dimitrios Lappas, Panagiotis Karampelas, Joshua E Siegel, Ioannis Templalexis, Stavros Stavrou, Sriram Krishnan
{"title":"Generic Drone Simulator: Design, Development and User Testing in a Virtual Search and Rescue Mission.","authors":"Georgios Pappas, Dimitrios Lappas, Panagiotis Karampelas, Joshua E Siegel, Ioannis Templalexis, Stavros Stavrou, Sriram Krishnan","doi":"10.1109/MCG.2025.3560537","DOIUrl":"https://doi.org/10.1109/MCG.2025.3560537","url":null,"abstract":"<p><p>This study addresses the need for scenario-specific drone simulators to enhance research, education, pilot training, and performance evaluation across diverse mission contexts. A gamified simulator was developed for the joint master's degree program \"Security and Defence\" between the Open University of Cyprus (OUC) and the Hellenic Air Force Academy (HAFA), with a focus on Search and Rescue mission training and planning. The simulator balances interface design, physics accuracy, and environmental realism to support specialized professional training and research. A survey-based evaluation involving 57 participants -pilots, engineers, and air traffic controllers -demonstrated the tool's ability to provide realistic experiences for trained pilots and meaningful learning opportunities for novices. Statistical analysis revealed significant correlations between gaming familiarity, task completion times, and participant expertise.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144052463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Efficient Stereo-Aware Screen-Space Ambient Occlusion with Adaptive Computation.","authors":"Yu-Ting Wu","doi":"10.1109/MCG.2025.3560155","DOIUrl":"https://doi.org/10.1109/MCG.2025.3560155","url":null,"abstract":"<p><p>Screen-space ambient occlusion (SSAO) has become a widely used technique in real-time rendering, valued for its high performance and full support for dynamic geometry. However, applying SSAO directly to stereo rendering can result in incorrect depth perception and viewer discomfort due to differences in captured scene approximations between the left and right views. Existing methods for generating stereo-consistent SSAO often involve substantial computational costs. This paper introduces an adaptive method, inspired by Weber's law, to enhance the efficiency of achieving stereo-consistent SSAO. Our method identifies inconsistent pixels generated by cost-effective SSAO algorithms, such as monoscopic SSAO, and selectively applies computationally intensive stereo-aware computations only to those pixels. Experiments demonstrate that our method delivers stereo-consistent results comparable to state-of-the-art techniques while significantly enhancing rendering performance.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144022810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"From Exploration to Critique: Catalyzing Critical Inquiry with Cultural Collection Visualizations.","authors":"Florian Windhager, Eva Mayr, Katrin Glinka","doi":"10.1109/MCG.2025.3559769","DOIUrl":"https://doi.org/10.1109/MCG.2025.3559769","url":null,"abstract":"<p><p>This paper examines whether visualizations in cultural heritage fields can move beyond their traditional roles of exploration and analysis to facilitate higher-order cognitive processes central to the practice of \"critique\". Drawing on arts and humanities perspectives, we define critical cognition as a mode of inquiry that explores and evaluates the potentiality of cultural objects and topics-and interrogates the associated representation and research systems that shape them-against the background of their actual state. We propose a framework for thinking about the critical potential of visualization systems and outline design strategies that enhance critical cognition and encourage responsive action. To that end, we examine multiple system components, including culture and context, collection practices, digital modeling, visualization, and research practices. We argue that by incorporating critical perspectives on these system components into interface design, we can empower users, foster more reflective and nuanced engagement with cultural collections, deepen understanding of their social, historical, and epistemic contexts, and ultimately strengthen trust in visualization methods within the arts and humanities.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144035748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Francesca Morini, Manuela Garreton, Jona Pomerance, Nadia Zeissig, Sabine de Guenther, Fidel Thomet, Linda Freyberg, Ilias Kyriazis, Andrea Scholz, Marian Dork
{"title":"Critical Interactivity: Exploration and Narration in Data Visualization.","authors":"Francesca Morini, Manuela Garreton, Jona Pomerance, Nadia Zeissig, Sabine de Guenther, Fidel Thomet, Linda Freyberg, Ilias Kyriazis, Andrea Scholz, Marian Dork","doi":"10.1109/MCG.2025.3544684","DOIUrl":"https://doi.org/10.1109/MCG.2025.3544684","url":null,"abstract":"<p><p>We propose critical interactivity as a concept to study and design the dynamic and transitory aspects of data visualizations. Theoretically, interactivity is often described as the means to support analytical tasks, while in practice, it encompasses the techniques that alter visual representations. These notions are a useful starting point to study the role of interactivity in critical engagements with data visualizations. At the core of critical interactivity is the negotiation of authority and agency: authority as authors provide structure and context, and agency as viewers navigate and interpret the data on their own terms. This raises the critical question: who has the power to control the visualization? Drawing from four case studies in science communication, art history, anthropology, and climate advocacy, we examine how critical interactivity links exploration and narration. We reflect on the effort involved in preparing data, and propose design strategies for implementing critical interactivity in data visualization.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143812859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jasmine T Otto, Malika Khurana, Noah Deutsch, Benjamin P S Donitz, Oskar Elek, Scott Davidoff
{"title":"MarsIPAN: Optimization and Negotiations in Mars Sample Return Scheduling Coordination.","authors":"Jasmine T Otto, Malika Khurana, Noah Deutsch, Benjamin P S Donitz, Oskar Elek, Scott Davidoff","doi":"10.1109/MCG.2025.3558426","DOIUrl":"https://doi.org/10.1109/MCG.2025.3558426","url":null,"abstract":"<p><p>Resource allocation problems touch almost every aspect of modernity. We examine communication bandwidth optimization and negotiation in NASA's early stage Mars Sample Return (MSR) mission, which places multiple robots into a single region on Mars. We present a design study conducted over two years at the NASA Jet Propulsion Laboratory with MSR, which characterizes the design and evaluation of the deployed MarsIPAN schedule browser. We find that MarsIPAN changes the schedule analysis process, providing new insight into how bandwidth is allocated, and enabling individual spacecraft teams to openly negotiate for scarce resources. This visibility leads to changes in how spacecraft teams apportion bandwidth, plan staffing, and organize and share resources. We reflect on the design study methodology as revealing, documenting, and supporting existing communication processes and software infrastructure within knowledge-intensive organizations.</p>","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143804900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}