The Workshop on Virtual Humans (WVH) will gather researchers and practitioners to explore the modeling, animation, and interaction with realistic digital humans. The event will cover topics in computer graphics, animation, computer vision, human perception, and AI-driven behaviors, aiming to bridge technical advances and human-centered design.
Prof. Daniel Thalmann is a Swiss and Canadian Computer Scientist. He is currently Honorary Professor at EPFL, Switzerland and Director of Research Development at MIRALab Sarl. Pioneer in research on Virtual Humans, his current research interests also include social robots, crowd simulation and Virtual Reality. Daniel Thalmann has been the Founder of The Virtual Reality Lab (VRlab) at EPFL, Switzerland, Professor at The University of Montreal and Visiting Professor/ Researcher at CERN, University of Nebraska, University of Tokyo, and National University of Singapore. He is coeditor-in-chief of the Journal of Computer Animation and Virtual Worlds, and member of the editorial board of 12 other journals. He is coeditor of 30 books, and coauthor of several books including 'Crowd Simulation' (second edition 2012) and 'Stepping Into Virtual Reality' (second edition in 2023), published by Springer. He received his PhD in Computer Science in 1977 from the University of Geneva and an Honorary Doctorate from University Paul-Sabatier in Toulouse, France, in 2003. He also received the Eurographics Distinguished Career Award in 2010, the 2012 Canadian Human Computer Communications Society Achievement Award, and the CGI 2015 Career Achievement. Daniel Thalmann is one of the most highly cited scientists in Computer Graphics (Google scholar h-index 98).
TBD
Dr. Paula Dornhofer Paro Costa is a professor at the University of Campinas (Unicamp) and Head of the Department of Computer Engineering and Automation at FEEC. Her research bridges multimodal generative AI and cognitive modeling, with a focus on designing expressive and socially intelligent virtual humans. She leads projects on facial animation, gesture, and speech synthesis, exploring how emotion and communicative style foster trust and engagement. She is also a lead researcher at Unicamp’s Hub for Artificial Intelligence and Cognitive Architectures (H.IAAC), a multidisciplinary initiative dedicated to modeling aspects of the human mind. Her work connects embodiment and cognition as complementary paths toward socially grounded AI.
Virtual humans have traveled a long path, evolving from rule-based systems into today’s multimodal agents powered by large language models. Along this trajectory, important contributions have emerged from Brazil and beyond, expanding both the technical capabilities and the cultural reach of these systems. Current advances demonstrate how LLMs can provide coherence, context awareness, and expressive interaction, but they also raise new challenges for computer graphics, such as the believable synthesis of faces, gestures, and affective expression. The next horizon lies in virtual humans with cognitive depth — agents that can remember, adapt, and display affective states shaped by experience. Advancing toward this vision requires the combined progress of computer graphics, artificial intelligence, and cognitive architectures, working together to faithfully translate cognition into embodied, expressive presence. Such progress must remain grounded in cultural sensitivity, ethics, and social responsibility, so that cognitive virtual humans emerge not as tools but as evolving partners in human diversity.
Prof. Theodore Kim is a full Professor of CS at Yale, where he co-leads the Computer Graphics Group alongside Julie Dorsey and Holly Rushmeier. He researches topics in physics-based simulation, including fire, water, and humans. His work has appeared in over two dozen movies, receiving a SciTech Oscar in both 2012 and 2022. Many of the results can be seen on YouTube, and extensive source code is available on his page. Previously, he was a Senior Research Scientist at Pixar Research, where he received screen credits in Cars 3, Coco, Incredibles 2, and Toy Story 4. His first (uncredited) work appeared on-screen on the Sorting Hat in Harry Potter and the Sorcerer's Stone. He is also an Associate Editor for ACM Transactions on Graphics.
Today, it is widely believed that the CGI algorithms for generating virtual humans can even-handedly depict all forms of humanity. This is false, and in fact many of these algorithms only excel at the features of socially dominant groups: pale skin and straight hair. In this talk, I will present our work on depicting highly coiled hair, otherwise known as "Afro-textured" or "kinky" hair. I will show that when we break the assumption that straight hair is a universal stand-in for all hair, a variety of interesting scientific phenomena immediately appear.
The full-day (7-hour) workshop will include:
We invite short papers (maximum 4 pages) on all topics related to virtual humans, including modeling, animation, AI, perception, and applications.
Accepted papers will be published in the SIBGRAPI Extended Proceedings with posterior invitation to be published at JBCS.
The Latex template is available here.
Please follow the included instructions and the formatting guidelines, avoiding any change to the format
(in particular, avoiding \vspace command or creating subsections or paragraph titles with any command different from \subsection or \paragraph).
The references should be formatted accordingly. Please do not change the font size, even if it helps to comply with the page limit.
The illustrations of the paper should be generated either truly vectorial or rasterized with at least 300 dpi.
Paper submission will be handled via the CMT system through this link.
For people who asked for more information about John, its .exe can be found here. Please, keep in mind that we are using a free version of a LLM tool, so it is possible that he stops answering after many uses.
For inquiries, email us at: soraia.musse@pucrs.br