Virtual Instrument Performances (VIP): A Comprehensive Review

Theodoros Kyriakou, Mercè Álvarez, Andreas Panayiotou, Yiorgos Chrysanthou, Panayiotis Charalambous, Andreas Aristidou

Computer Graphics Forum, Volume 43, Issue 2, Apr 2024

Presented at: Eurographics 2024, EG'24 STAR papers

The evolving landscape of performing arts, driven by advancements in Extended Reality (XR) and the Metaverse, presents transformative opportunities for digitizing musical experiences. This comprehensive survey explores the relatively unexplored field of Virtual Instrument Performances (VIP), addressing challenges related to motion capture precision, multi-modal interactions, and the integration of sensory modalities, with a focus on fostering inclusivity, creativity, and live performances in diverse settings.

Digitizing Traditional Dances Under Extreme Clothing: The Case Study of Eyo

Temi Ami-Williams, Christina-Georgia Serghides, Andreas Aristidou

Journal of Cultural Heritage, Mar 2024

Presented at: The International Council for Traditional Music (ICTM) 2023 and the Cyprus Dance Film Festival (CDFF) 2023

This work examines the challenges of capturing movements in traditional African masquerade garments, specifically the Eyo masquerade dance from Lagos, Nigeria. By employing a combination of motion capture technologies, the study addresses the limitations posed by "extreme clothing" and offers valuable insights into preserving cultural heritage dances. The findings lead to an efficient pipeline for digitizing and visualizing folk dances with intricate costumes, culminating in a visually captivating animation showcasing an Eyo masquerade dance performance.

DOI paper video project page

P2C: A Paths-to-Crowds Framework to Parameterize Behaviors

Marilena Lemonari, Andreas Panayiotou, Nuria Pelechano, Theodoros Kyriakou, Yiorgos Chrysanthou, Andreas Aristidou, Panayiotis Charalambous

IEEE Transactions on Visualization and Computer Graphics, Submitted., Jan 2024

We present P2C, a method for simulating realistic and diverse crowds by parameterizing reference crowd data. This approach enables fine-grained control, allowing artists to modify intuitive behavior parameters in localized regions during runtime, facilitating the creation of customizable agent behaviors and interactions in crowd simulations. The method integrates four fundamental behaviors into an existing Reinforcement Learning-based system and demonstrates its potential through predictive power evaluation on real data, comparing favorably against existing baselines.

paper video project page

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

Jose Luis Pontón, Haoran Yun, Andreas Aristidou, Carlos Andújar, Nuria Pelechano

ACM Transactions on Graphics, Volume 43, Issue 1, Article No.: 5, pages 1–14., Oct 2023

Presented at: SIGGRAPH Asia 2023.

SparsePoser is a novel deep learning-based approach that reconstructs full-body poses using only six tracking devices. The system uses a convolutional autoencoder to generate high-quality human poses learned from motion capture data and a lightweight feed-forward neural network IK component to adjust hands and feet based on the corresponding trackers.

DOI paper video code bibtex project page

Collaborative VR: Solving riddles in the concept of escape rooms

Afxentis Ioannou, Marilena Lemonari, Fotis Liarokapis, Andreas Aristidou

Presented at: International Conference on Interactive Media, Smart Systems and Emerging Technologies, IMET, Oct 2023

This work explores alternative means of communication in collaborative virtual environments (CVEs) and their impact on users' engagement and performance. Through a case study of a collaborative VR escape room, we conduct a user study to evaluate the effects of nontraditional communication methods in computer-supported cooperative work (CSCW). Despite the absence of traditional interactions, our study reveals that users can effectively convey messages and complete tasks, akin to real-life scenarios.

DOI paper bibtex

Let's All Dance: Enhancing Amateur Dance Motions

Qiu Zhou, Manyi Li, Qiong Zeng, Andreas Aristidou, Xiaojing Zhang, Lin Chen, Changhe Tu

Computational Visual Media, Vol.9, No.3., Sep 2023

In this paper, we present a deep model that enhances professionalism to amateur dance movements, allowing the movement quality to be improved in both the spatial and temporal domains. We illustrate the effectiveness of our method on real amateur and artificially generated dance movements. We also demonstrate that our method can synchronize 3D dance motions with any reference audio under non-uniform and irregular misalignment.

DOI paper video code database project page

Dancing in virtual reality as an inclusive platform for social and physical fitness activities: A survey

Bhuvaneswari Sarupuri, Richard Kulpa, Andreas Aristidou, Franck Multon

The Visual Computer, Aug 2023

This paper qualitatively evaluates 292 users of a VR dancing platform, exploring their motivations, experiences, and requirements. We employ OpenAI's Artificial Intelligence platform for automatic extraction of response categories. The focus is on VR as an inclusive platform for social and physical dancing activities.

DOI paper database bibtex

Collaborative Museum Heist with Reinforcement Learning

Eleni Evripidou, Andreas Aristidou, Panayiotis Charalambous

Computer Animation and Virtual Worlds, Volume 34, Issue 3-4, May 2023., May 2023

Presented at: 36th International Conference on Computer Animation and Social Agents, CASA'23

In this paper, we present our initial findings of applying Reinforcement Learning techniques to a museum heist game, where trained robbers with different skills learn to cooperate and maximize individual and team rewards while avoiding detection by scripted security guards and cameras, showcasing the feasibility of training both sides concurrently in an adversarial game setting.

DOI paper video code bibtex

Motion-R^3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking

Jubo Yu, Tianxiang Ren, Shihui Guo, Fengyi Fang, Kai Wang, Zijiao Zeng, Yazhan Zhang, Andreas Aristidou, Yipeng Qin > cs > arXiv:2304.01672, Apr 2023

In this work we present a new method for motion annotation based on the representativeness of motion data in a given dataset. Our ranks motion data based on their representativeness in a learned motion representation space. The paper also introduces a dual-level motion contrastive learning method to learn the motion representation space in a more informative way. The proposed method is efficient and can adapt to frequent requirements changes, enabling agile development of motion annotation models.


Virtual Library in the concept of digital twins

Nikolas Iakovides, Andreas Lazarou, Panayiotis Kyriakou, Andreas Aristidou

Presented at: International Conference on Interactive Media, Smart Systems and Emerging Technologies, IMET, Oct 2022

In this work, we reconstruct the Limassol Municipal University Library in the concept of a digital twin. To do so, we conducted a perceptual survey to understand the current use of physical libraries, examine the user’s experience with VR, and identify potential use cases of VR libraries. Based on the outcome, we design five use case scenarios where we demonstrate the potential use of virtual libraries.

DOI paper video project page

Digitizing Wildlife: The case of reptiles 3D virtual museum

Savvas Zotos, Marilena Lemonari, Michael Konstantinou, Anastasios Yiannakidis, Georgios Pappas, Panayiotis Kyriakou, Ioannis N. Vogiatzakis, Andreas Aristidou

IEEE Computer Graphics and Applications, Feature Article, Volume 42, Issue 5., Sep 2022

In this paper, we design and develop a 3D virtual museum with holistic metadata documentation and a variety of captured reptile behaviors and movements. Our main contribution lies on the procedure of rigging, capturing, and animating reptiles, as well as the development of a number of novel educational applications.

DOI paper video project page

Pose Representations for Deep Skeletal Animation

Nefeli Andreou, Andreas Aristidou, Yiorgos Chrysanthou

Computer Graphics Forum, Volume 41, Issue 8, Sep 2022

Presented at: ACM SIGGRAPH/ Eurographics Symposium on Computer Animation, SCA'22. Eurographics Association

In this work we present an efficient method for training neural networks, specifically designed for character animation. We use dual quaternions as the mathematical framework, and we take advantage of the skeletal hierarchy, to avoid rotation discontinuities, a common problem when using Euler angle or exponential map parameterizations, or motion ambiguities, a common problem when using positional data. Our method does not requires re-projection onto skeleton constraints to avoid bone stretching violation and invalid configurations, while the network is propagated learning using both rotational and positional information.

DOI paper video code project page

CCP: Configurable Crowd Profiles

Andreas Panayiotou, Theodoros Kyriakou, Marilena Lemonari, Yiorgos Chrysanthou, Panayiotis Charalambous

Presented at: SIGGRAPH ’22 Conference Proceedings, Aug 2022

In this paper, we present a RL-based framework for learning multiple agent behaviors concurrently. We optimize the agent by varying the importance of the selected behaviors (goal seeking, collision avoidance, interaction with environment, and grouping) while training; essentially we have a reward function that changes dynamically during training. The importance of each separate sub-behavior is added as input to the policy, resulting in the development of a single model capable of capturing as well as enabling dynamic run-time manipulation of agent profiles; thus allowing configurable profiles.

DOI paper video code

Authoring Virtual Crowds: A Survey

Marilena Lemonari, Rafael Blanco, Panayiotis Charalambous, Nuria Pelechano, Marios Avraamides, Julien Pettré, Yiorgos Chrysanthou

Computer Graphics Forum, Volume 41, Issue 2, Pages 677-701, May 2022

Presented at: Eurographics 2022 - STAR

In this survey, we provide a review of the most relevant methods in authoring virtual crowds, emphasizing the amount and nature of influence that the users have over the final result. We discuss the currently available authoring tools (e.g., graphical user interfaces, drag-and-drop), identifying the trends of early and recent work, and we suggest promising directions for future research that mainly stem from the rise of learning-based methods, and the need for a unified authoring framework.


Safeguarding our Dance Cultural Heritage

Andreas Aristidou, Alan Chalmers, Yiorgos Chrysanthou, Celine Loscos, Franck Multon, Joseph E. Parkins, Bhuvan Sarupuri, Efstathios Stavrakis

Presented at: Eurographics 2022 - Tutorials, May 2022

In this tutorial, we show how the European Project, SCHEDAR, exploited emerging technologies to digitize, analyze, and holistically document our intangible heritage creations, that is a critical necessity for the preservation and the continuity of our identity as Europeans.

DOI paper video project page