Publications
MotionPyramid: Controllable Motion Synthesis via Stylized Phase Manifolds
Jingyuan Li, Peizhuo Li, Andreas Aristidou, Olga Sorkine-Hornung
Computer Graphics Forum, Jul 2026
Presented at: 25th ACM SIGGRAPH / Eurographics Symposium on Computer Animation (SCA 2026), Barcelona, Spain
MotionPyramid introduces stylized phase manifolds, a compact and interpretable latent representation that disentangles motion semantics, temporal dynamics, and style in an unsupervised, low-dimensional space. By using this representation as a structured bridge between text and motion, MotionPyramid enables fine-grained control over diffusion-based motion generation, producing high-quality, diverse motions with improved text-to-motion alignment.
MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance
Nathan Sala, Ofir Abramovich, Ariel Shamir, Daniel Cohen-Or, Andreas Aristidou, Sigal Raab
Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference, Conference Papers, Jul 2026
Presented at: SIGGRAPH Conference Papers '26
We introduce MultiAct, an inference-time method that enhances pretrained text-to-motion models to better capture multiple simultaneous actions. By adaptively boosting attention to underrepresented prompt components, it improves semantic completeness without retraining, achieving stronger results on complex prompts.
Mixed Reality in Electronic Health Records: User Requirements and Evaluation
Silouanos Chaldoupis, Eirini Schizas, Andreas Aristidou
Presented at: 39th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2026, Limassol, Cyprus, Jun 2026
We present an MR-enhanced Electronic Health Record system that enables intuitive exploration of multimodal patient data through spatial, holographic interfaces. Our approach integrates clinical information, including 3D medical imaging, into an interactive mixed reality environment, demonstrating improved usability, anatomical understanding, and support for collaborative and patient-centered care.
A novel multidisciplinary approach for reptile movement and behavior analysis
Savvas Zotos, Marilena Stamatiou, Sofia-Zacharenia Marketaki, Duncan J. Irschick, Jeremy A. Bot, Andreas Aristidou, Emily L. C. Shepard, Mark D. Holton, Ioannis N. Vogiatzakis
Integrative Zoology, Volume21, Issue3, Pages 468-484, May 2026
This paper introduces a multidisciplinary approach to studying reptile behavior, combining tri-axial accelerometers, video recordings, motion capture systems, and 3D reconstruction to create detailed digital archives of movements and behaviors. Using two Mediterranean reptiles as case studies, it highlights the potential of this method to advance research on complex and understudied behaviors, offering ecological insights and tools for behavioral analysis.
Interactive Engineering Training Framework in Mixed Reality Environments
Christina-Georgia Serghides, Andreas Aristidou
Presented at: International Workshop on eXtended Reality for Industrial and Occupational Supports (XRIOS), part of IEEE VR 2026 conference, Daegu, Korea,, Mar 2026
We present a Mixed Reality–based framework for collaborative engineering training in aerospace and automotive maintenance and assembly, addressing the complexity, safety, and procedural demands of traditional hands-on methods. By building on existing computer-based and VR/AR approaches, the proposed platform bridges the gap between physical training and digital solutions, enabling more efficient, cost-effective, and collaborative training experiences.
Disaster evacuation of the old city of Nicosia
Marios Stylianou, Marios Demetriou, Andreas Aristidou
Progress in Disaster Science, Special Issue: AI, Emerging Technologies, and Immersive Solutions for Disaster and Emergency Response, Elsevier, Mar 2026
Presented at: 8th International Disaster and Risk Conference, IDRC 2025, Nicosia, Cyprus, Oct. 2025
This paper presents a digital twin–based simulation of evacuation scenarios in Nicosia’s historic walled Old Town, showing how dense urban morphology, gate blockages, and infrastructure changes affect evacuation efficiency and highlighting the need for coordinated, adaptive flow-management strategies to reduce disaster risks in historic cities.
Mocap Anywhere: Pairwise Distance-based Motion Capture in the Wild, for the Wild
Ofir Abramovich, Ariel Shamir, Andreas Aristidou
arXiv.org > cs.CV > arXiv:2601.19519, Jan 2026
We introduce Wild-Poser (WiP), a real-time Transformer-based system that reconstructs full-body 3D motion from sparse pairwise distance measurements using body-mounted UWB sensors, without cameras or environmental constraints. WiP robustly predicts accurate 3D joint positions from noisy data and generalizes across diverse human and non-human morphologies in real-world settings.
CrowdImprint: decomposing context-aware interactions
Marilena Lemonari, Panayiotis Charalambous, Julien Pettré, Yiorgos Chrysanthou
The Visual Computer, 42(128), Jan 2026
We present a model that learns how people interact with specific objects or “sources” by analyzing trajectories, decomposing movements into simple core behaviours (e.g., approach, stop, circle). It builds distributions of these behaviours to summarise and generate context-aware crowd interactions, demonstrating usefulness for tasks like behaviour comparison.
Procedural Modelling of Aged Buildings: A Case Study of Mudbrick Houses in Cyprus
Christos Othonos, Gonzalo Besuievsky, Melinos Averkiou, Loizos Pelecanos, Gustavo Patow, Yiorgos Chrysanthou
ACM Journal on Computing and Cultural Heritage, 18(4), Article No.: 70, Pages 1 - 18, Dec 2025
We present a system for procedurally generating aged buildings by simulating weathering and material degradation using finite element analysis. Integrated into building generators, it models aging effects like erosion and structural changes, demonstrated on Cypriot mudbrick houses and useful for cultural heritage visualization and analysis.
DRUMS: Drummer Reconstruction Using Midi Sequences
Theodoros Kyriakou, Panayiotis Charalambous, Andreas Aristidou
Presented at: 18th annual ACM SIGGRAPH conference on Motion, Interaction and Games, MIG 2025, Zurich, Switzerland, Dec 2025
DRUMS is a MIDI-driven system that generates expressive, full-body drumming performances, combining precise rhythmic accuracy with realistic hand, stick, upper-body, and facial movements. By integrating BiLSTM-based hand motion prediction, phrase-matched upper-body and facial expressions, and procedural foot control through a modular IK framework, our method produces visually convincing and musically aligned drummer animations for applications in digital performance.
MPACT: Mesoscopic Profiling and Abstraction of Crowd Trajectories
Marilena Lemonari, Andreas Panayiotou, Theodoros Kyriakou, Nuria Pelechano, Yiorgos Chrysanthou, Andreas Aristidou, Panayiotis Charalambous
Computer Graphics Forum, Volume 44, Issue 6., Sep 2025
MPACT is a framework that transforms unlabelled crowd data into controllable simulation parameters using image-based encoding and a parameter prediction network trained on synthetic image–profile pairs. It enables intuitive crowd authoring and behavior analysis, achieving high scores in believability, plausibility, and behavioral fidelity across evaluations and user studies.
Interactive Media for Cultural Heritage
Fotis Liarokapis, Maria Shehade, Andreas Aristidou, Yiorgos Chrysanthou
Springer Nature Switzerland, Jul 2025
This edited book explores the latest advancements in interactive media applied to Digital Cultural Heritage research, covering areas from visual data acquisition to immersive experiences like extended reality and digital storytelling. Structured into four sections, it offers theoretical discussions and diverse case studies, making it a valuable resource for academics, scholars, researchers, and students interested in interdisciplinary approaches to cultural heritage preservation and exploration through emerging technologies.
Motion labelling and recognition: A case study on the Zeibekiko dance
Maria Skublewska-Paszkowska, Pawel Powroznik, Marilena Lemonari, Andreas Aristidou
Interactive Media for Cultural Heritage, Jul 2025
This work employs Spatial Temporal Graph Convolutional Networks (ST-GCN) to recognize and annotate folk dance movements, using the Greek Zeibekiko dance as a case study to address the challenges of motion segmentation in complex, expressive dances. By enabling accurate classification and annotation of motion-captured dance data, the method supports cultural heritage preservation, dance analysis, and educational applications.
Multi - Modal Signal Processing for Avatar Motion Adaptation
Amir Azizi, Panayiotis Charalambous, Yiorgos Chrysanthou
Presented at: The 25th International Conference on Digital Signal Processing (DSP), Jun 2025
We propose a multi-modal framework for adapting avatar motion using an encoder–decoder architecture with phase-based features, enabling control over attributes like speed and intensity. By integrating inputs such as text, speech, video, and webcam data, the approach allows flexible and intuitive motion adjustment, demonstrating efficient and scalable performance across multiple datasets.
DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization
Jose Luis Pontón, Eduard Pujol, Andreas Aristidou, Carlos Andújar, Nuria Pelechano
Computer Graphics Forum, Volume 44, Issue 2., Apr 2025
Presented at: Eurographics 2025, EG'25 proceedings
DragPoser is a deep-learning-based motion reconstruction system that uses variable sparse sensors as input, achieving real-time high end-effector position accuracy through a pose optimization process within a structured latent space. Incorporating a Temporal Predictor network with a Transformer architecture, DragPoser surpasses traditional methods in precision, producing natural and temporally coherent poses, and demonstrating robustness and adaptability to dynamic constraints and various input configurations.