arXiv subjects

George Papagiannakis

Publications and source records attributed to George Papagiannakis.

At least 19 recordsLinked to original sources

arXiv2026

Conformal Geometric Algebra as a Symbolic Interface for LLM-Driven 3D Scene Editing

What symbolic format should an LLM emit for reliable 3D scene editing from natural language, and does algebraic structure help beyond compact syntax? We evaluate Conformal Geometric Algebra (CGA) as a compact symbolic interface against a verbose Euclidean 4$\times$4 matrix baseline and a non-CGA Compact SE3 control in a natural-language 3D editing pipeline with controlled prompting and deterministic geometric execution. Our primary result is compositional fidelity under sequential instruction chains. In a sequence-stress protocol (20 templates, 6 trials each; $\texttt{n=120}$ outputs per method), Simple CGA and Compact SE3 both achieve 100% parse validity, but Simple CGA preserves exact ordered operation chains more reliably (97.5% vs 90.0%, two-proportion $\texttt{p=0.016}$) with lower completion-token cost (112.6 vs 133.6 tokens). This pattern is consistent with algebraic expression form supporting compositional faithfulness beyond compactness alone. A second result is confirmatory in the powered hard semantic suite ($\texttt{n=100}$ per method): compact representations (Simple CGA 45.0%, Compact SE3 42.0%, Shenlong 44.0%) all exceed the Euclidean 4$\times$4 baseline (24.0%). Simple CGA vs Euclidean is +21 pp ($\texttt{p=0.0028}$) and Compact SE3 vs Euclidean is +18 pp ($\texttt{p=0.0103}$), while Simple CGA vs Compact SE3 is statistically close ($\texttt{p=0.7755}$). Separating parse validity from geometric correctness reveals substantial optimization headroom invisible to syntax-only metrics. Overall, compact symbolic interfaces appear to drive reliability-cost gains, with CGA motor composition providing an additional advantage on ordered instruction chains. These findings inform real-time natural-language editing in immersive and interactive 3D environments.

cs.GR↗

arXiv2025

The Uncanny Valley in medical simulation-based training: a visual summary

The purpose of this review article is to provide a bibliographical as well as evidence-based visual guide regarding the effect of ``Uncanny Valley'' (UV) and how it profoundly influences medical virtual reality simulation-based training. The phenomenon, where increasingly realistic virtual humans elicit discomfort due to subtle imperfections, is crucial to understand and address in the context of medical training, where realism and immersion are key to effective learning. Our research team, consisting of experts in computer graphics, virtual reality, and medical education, brings a diverse and multidisciplinary perspective to this subject. Our collective experience spans developing advanced computer graphics systems, VR character simulation, and innovative educational technologies. We have collaborated across institutions and industries to push the boundaries of VR applications in medical training.

cs.GR↗

arXiv2025

One algebra for all : Geometric Algebra methods for neurosymbolic XR scene authoring, animation and neural rendering

This position paper delves into the transformative role of Geometric Algebra (GA) in advancing specific areas of Computer Graphics (CG) and Extended Reality (XR), particularly in character animation, rendering, rigging, neural rendering, and generative AI-driven scene editing. Common CG algorithms require handling rotations, translations, and dilations (uniform scalings) in operations such as object rendering, rigged model animation, soft-body deformation, and XR simulations. Traditional representation forms - such as matrices, quaternions, and vectors - often introduce limitations in precision and performance. Recent breakthroughs in the use of GA suggest it can significantly enhance these processes by encapsulating geometric forms and transformations into uniform algebraic expressions, which maintain critical geometric properties throughout multi-step transformations. Furthermore, we explore how GA can serve as a unifying mathematical substrate for neurosymbolic XR scene authoring, bridging learned neural representations and explicit geometric reasoning. This paper outlines how GA-based approaches can improve the fidelity of rigged character animations, enhance soft-body simulations, streamline real-time rendering, and optimize neural and generative AI scene editing. GA offers a coherent and efficient framework for these processes, resulting in superior visual outcomes and computational efficiency, particularly in XR environments.

cs.GR↗

arXiv2025

Geometric Algebra Meets Large Language Models: Instruction-Based Transformations of Separate Meshes in 3D, Interactive and Controllable Scenes

This paper introduces a novel integration of Large Language Models (LLMs) with Conformal Geometric Algebra (CGA) to revolutionize controllable 3D scene editing, particularly for object repositioning tasks, which traditionally requires intricate manual processes and specialized expertise. These conventional methods typically suffer from reliance on large training datasets or lack a formalized language for precise edits. Utilizing CGA as a robust formal language, our system, Shenlong, precisely models spatial transformations necessary for accurate object repositioning. Leveraging the zero-shot learning capabilities of pre-trained LLMs, Shenlong translates natural language instructions into CGA operations which are then applied to the scene, facilitating exact spatial transformations within 3D scenes without the need for specialized pre-training. Implemented in a realistic simulation environment, Shenlong ensures compatibility with existing graphics pipelines. To accurately assess the impact of CGA, we benchmark against robust Euclidean Space baselines, evaluating both latency and accuracy. Comparative performance evaluations indicate that Shenlong significantly reduces LLM response times by 16% and boosts success rates by 9.6% on average compared to the traditional methods. Notably, Shenlong achieves a 100% perfect success rate in common practical queries, a benchmark where other systems fall short. These advancements underscore Shenlong's potential to democratize 3D scene editing, enhancing accessibility and fostering innovation across sectors such as education, digital entertainment, and virtual reality.

cs.CV↗

arXiv2025

Neural-GASh: A CGA-based neural radiance prediction pipeline for real-time shading

This paper presents Neural-GASh, a novel real-time shading pipeline for 3D meshes, that leverages a neural radiance field architecture to perform image-based rendering (IBR) using Conformal Geometric Algebra (CGA)-encoded vertex information as input. Unlike traditional Precomputed Radiance Transfer (PRT) methods, that require expensive offline precomputations, our learned model directly consumes CGA-based representations of vertex positions and normals, enabling dynamic scene shading without precomputation. Integrated seamlessly into the Unity engine, Neural-GASh facilitates accurate shading of animated and deformed 3D meshes - capabilities essential for dynamic, interactive environments. The shading of the scene is implemented within Unity, where rotation of scene lights in terms of Spherical Harmonics is also performed optimally using CGA. This neural field approach is designed to deliver fast and efficient light transport simulation across diverse platforms, including mobile and VR, while preserving high rendering quality. Additionally, we evaluate our method on scenes generated via 3D Gaussian splats, further demonstrating the flexibility and robustness of Neural-GASh in diverse scenarios. Performance is evaluated in comparison to conventional PRT, demonstrating competitive rendering speeds even with complex geometries.

cs.GR↗

arXiv2025

Non-linear, Team-based VR Training for Cardiac Arrest Care with enhanced CRM Toolkit

This paper introduces iREACT, a novel VR simulation addressing key limitations in traditional cardiac arrest (CA) training. Conventional methods struggle to replicate the dynamic nature of real CA events, hindering Crew Resource Management (CRM) skill development. iREACT provides a non-linear, collaborative environment where teams respond to changing patient states, mirroring real CA complexities. By capturing multi-modal data (user actions, cognitive load, visual gaze) and offering real-time and post-session feedback, iREACT enhances CRM assessment beyond traditional methods. A formative evaluation with medical experts underscores its usability and educational value, with potential applications in other high-stakes training scenarios to improve teamwork, communication, and decision-making.

cs.HC↗

arXiv2024

pyGANDALF -- An open-source, Geometric, ANimation, Directed, Algorithmic, Learning Framework for Computer Graphics

In computer graphics (CG) education, the challenge of finding modern, versatile tools is significant, particularly when integrating both legacy and advanced technologies. Traditional frameworks, often reliant on solid, yet outdated APIs like OpenGL, limit the exploration of cutting-edge graphics techniques. To address this, we introduce pyGANDALF, a unique, lightweight, open-source CG framework built on three pillars: Entity-Component-System (ECS) architecture, Python programming, and WebGPU integration. This combination sets pyGANDALF apart by providing a streamlined ECS design with an editor layer, compatibility with WebGPU for state-of-the-art features like compute and ray tracing pipelines, and a programmer-friendly Python environment. The framework supports modern features, such as Physically Based Rendering (PBR) capabilities and integration with Universal Scene Description (USD) formats, making it suitable for both educational demonstrations and real-world applications. Evaluations by expert users confirmed that pyGANDALF effectively balances ease of use with advanced functionality, preparing students for contemporary CG development challenges.

cs.GR↗

arXiv2024

Decoupled Edge Physics algorithms for collaborative XR simulations

This work proposes a novel approach to transform any modern game engine pipeline, for optimized performance and enhanced user experiences in Extended Reality (XR) environments. Decoupling the physics engine from the game engine pipeline and using a client-server N-1 architecture creates a scalable solution, efficiently serving multiple graphics clients on Head-Mounted Displays (HMDs) with a single physics engine on edge-cloud infrastructure. This approach ensures better synchronization in multiplayer scenarios without introducing overhead in single-player experiences, maintaining session continuity despite changes in user participation. Relocating the Physics Engine to an edge or cloud node reduces strain on local hardware, dedicating more resources to high-quality rendering and unlocking the full potential of untethered HMDs. We present four algorithms that decouple the physics engine, increasing frame rates and Quality of Experience (QoE) in VR simulations, supporting advanced interactions, numerous physics objects, and multi-user sessions with over 100 concurrent users. Incorporating a Geometric Algebra interpolator reduces inter-calls between dissected parts, maintaining QoE and easing network stress. Experimental validation, with more than 100 concurrent users, 10,000 physics objects, and softbody simulations, confirms the technical viability of the proposed architecture, showcasing transformative capabilities for more immersive and collaborative XR applications without compromising performance.

cs.HC↗

arXiv2024

A computational medical XR discipline

Computational Medical Extended Reality (CMXR), brings together life sciences and neuroscience with mathematics, engineering and computer science. It unifies computational science (scientific computing) with intelligent extended reality and spatial computing for the medical field. It significantly differs from previous "Clinical XR" or "Medical XR" terms, as it is focusing on how to integrate computational methods from neural simulation to computational geometry, computational vision and computer graphics with deep learning models to solve specific hard problems in medicine and neuroscience: from low/no-code/genAI authoring platforms to deep learning XR systems for training, planning, operative navigation, therapy and rehabilitation.

cs.GR↗

arXiv2024

VR Isle Academy: A VR Digital Twin Approach for Robotic Surgical Skill Development

Contemporary progress in the field of robotics, marked by improved efficiency and stability, has paved the way for the global adoption of surgical robotic systems (SRS). While these systems enhance surgeons' skills by offering a more accurate and less invasive approach to operations, they come at a considerable cost. Moreover, SRS components often involve heavy machinery, making the training process challenging due to limited access to such equipment. In this paper we introduce a cost-effective way to facilitate training for a simulator of a SRS via a portable, device-agnostic, ultra realistic simulation with hand tracking and feet tracking support. Error assessment is accessible in both real-time and offline, which enables the monitoring and tracking of users' performance. The VR application has been objectively evaluated by several untrained testers showcasing significant reduction in error metrics as the number of training sessions increases. This indicates that the proposed VR application denoted as VR Isle Academy operates efficiently, improving the robot - controlling skills of the testers in an intuitive and immersive way towards reducing the learning curve at minimal cost.

cs.RO↗

arXiv2024

GA-Unity: A Production-Ready Unity Package for Seamless Integration of Geometric Algebra in Networked Collaborative Applications

This paper introduces GA-Unity, the first Unity package specifically designed for seamless integration of Geometric Algebra (GA) into collaborative networked applications. Indeed, in such contexts, it has been demonstrated that using multivectors for interpolation between transmitted poses reduces runtime by 16% and bandwidth usage by an average of 50% compared to traditional representation forms (vectors and quaternions); we demonstrate that GA-Unity further enhances runtime performance. Tailored for 3D Conformal Geometric Algebra, GA-Unity also offers an intuitive interface within the Unity game engine, simplifying GA integration for researchers and programmers. By eliminating the need for users to develop GA functionalities from scratch, GA-Unity expedites GA experimentation and implementation processes. Its seamless integration enables easy representation of transformation properties using multivectors, facilitating deformations and interpolations without necessitating modifications to the rendering pipeline. Furthermore, its graphical interface establishes a GA playground for developers within the familiar confines of a modern game engine. In summary, GA-Unity represents a significant advancement in GA accessibility and usability, particularly in collaborative networked environments, empowering innovation and facilitating widespread adoption across various research and programming domains while upholding high-performance standards.

cs.GR↗

arXiv2023

Project Elements: A computational entity-component-system in a scene-graph pythonic framework, for a neural, geometric computer graphics curriculum

We present the Elements project, a lightweight, open-source, computational science and computer graphics (CG) framework, tailored for educational needs, that offers, for the first time, the advantages of an Entity-Component-System (ECS) along with the rapid prototyping convenience of a Scenegraph-based pythonic framework. This novelty allows advances in the teaching of CG: from heterogeneous directed acyclic graphs and depth-first traversals, to animation, skinning, geometric algebra and shader-based components rendered via unique systems all the way to their representation as graph neural networks for 3D scientific visualization. Taking advantage of the unique ECS in a a Scenegraph underlying system, this project aims to bridge CG curricula and modern game engines (MGEs), that are based on the same approach but often present these notions in a black-box approach. It is designed to actively utilize software design patterns, under an extensible open-source approach. Although Elements provides a modern (i.e., shader-based as opposed to fixed-function OpenGL), simple to program approach with Jupyter notebooks and unit-tests, its CG pipeline is not black-box, exposing for teaching for the first time unique challenging scientific, visual and neural computing concepts.

cs.GR↗

arXiv2023

UniSG^GA: A 3D scenegraph powered by Geometric Algebra unifying geometry, behavior and GNNs towards generative AI

This work presents the introduction of UniSG^GA, a novel integrated scenegraph structure, that to incorporates behavior and geometry data on a 3D scene. It is specifically designed to seamlessly integrate Graph Neural Networks (GNNs) and address the challenges associated with transforming a 3D scenegraph (3D-SG) during generative tasks. To effectively capture and preserve the topological relationships between objects in a simplified way, within the graph representation, we propose UniSG^GA, that seamlessly integrates Geometric Algebra (GA) forms. This novel approach enhances the overall performance and capability of GNNs in handling generative and predictive tasks, opening up new possibilities and aiming to lay the foundation for further exploration and development of graph-based generative AI models that can effectively incorporate behavior data for enhanced scene generation and synthesis.

cs.GR↗

arXiv2023

AR-Assisted Surgical Care via 5G networks for First Aid Responders

Surgeons should play a central role in disaster planning and management due to the overwhelming number of bodily injuries that are typically involved during most forms of disaster. In fact, various types of surgical procedures are performed by emergency medical teams after sudden-onset disasters, such as soft tissue wounds, orthopaedic traumas, abdominal surgeries, etc. HMD-based Augmented Reality (AR), using state-of-the-art hardware such as the Magic Leap or the Microsoft HoloLens, have long been foreseen as a key enabler for clinicians in surgical use cases, especially for procedures performed outside of the operating room. This paper describes the Use Case (UC) "AR-assisted emergency surgical care", identified in the context of the 5G-EPICENTRE EU-funded project. Specifically, the UC will experiment with holographic AR technology for emergency medical surgery teams, by overlaying deformable medical models directly on top of the patient body parts, effectively enabling surgeons to see inside (visualizing bones, blood vessels, etc.) and perform surgical actions following step-by-step instructions. The goal is to combine the computational and data-intensive nature of AR and Computer Vision algorithms with upcoming 5G network architectures deployed for edge computing so as to satisfy real-time interaction requirements and provide an efficient and powerful platform for the pervasive promotion of such applications. By developing the necessary Virtual Network Functions (VNFs) to manage data-intensive services (e.g., prerendering, caching, compression) and by exploiting available network resources and Multi-access Edge Computing (MEC) support, provided by the 5G-EPICENTRE infrastructure, this UC aims to provide powerful AR-based tools, usable on site, to first-aid responders.

cs.GR↗

arXiv2023

MAGES 4.0: Accelerating the world's transition to VR training and democratizing the authoring of the medical metaverse

In this work, we propose MAGES 4.0, a novel Software Development Kit (SDK) to accelerate the creation of collaborative medical training applications in VR/AR. Our solution is essentially a low-code metaverse authoring platform for developers to rapidly prototype high-fidelity and high-complexity medical simulations. MAGES breaks the authoring boundaries across extended reality, since networked participants can also collaborate using different virtual/augmented reality as well as mobile and desktop devices, in the same metaverse world. With MAGES we propose an upgrade to the outdated 150-year-old master-apprentice medical training model. Our platform incorporates, in a nutsell, the following novelties: a) 5G edge-cloud remote rendering and physics dissection layer, b) realistic real-time simulation of organic tissues as soft-bodies under 10ms, c) a highly realistic cutting and tearing algorithm, d) neural network assessment for user profiling and, e) a VR recorder to record and replay or debrief the training simulation from any perspective.

cs.GR↗

arXiv2022

Progressive tearing and cutting of soft-bodies in high-performance virtual reality

We present an algorithm that allows a user within a virtual environment to perform real-time unconstrained cuts or consecutive tears, i.e., progressive, continuous fractures on a deformable rigged and soft-body mesh model in high-performance 10ms. In order to recreate realistic results for different physically-principled materials such as sponges, hard or soft tissues, we incorporate a novel soft-body deformation, via a particle system layered on-top of a linear-blend skinning model. Our framework allows the simulation of realistic, surgical-grade cuts and continuous tears, especially valuable in the context of medical VR training. In order to achieve high performance in VR, our algorithms are based on Euclidean geometric predicates on the rigged mesh, without requiring any specific model pre-processing. The contribution of this work lies on the fact that current frameworks supporting similar kinds of model tearing, either do not operate in high-performance real-time or only apply to predefined tears. The framework presented allows the user to freely cut or tear a 3D mesh model in a consecutive way, under 10ms, while preserving its soft-body behaviour and/or allowing further animation.

cs.GR↗

arXiv2022

Less Is More: Efficient Networked VR Transformation Handling Using Geometric Algebra

As shared, collaborative, networked, virtual environments become increasingly popular, various challenges arise regarding the efficient transmission of model and scene transformation data over the network. As user immersion and real-time interactions heavily depend on VR stream synchronization, transmitting the entire data sat does not seem a suitable approach, especially for sessions involving a large number of users. Session recording is another momentum-gaining feature of VR applications that also faces the same challenge. The selection of a suitable data format can reduce the occupied volume, while it may also allow effective replication of the VR session and optimized post-processing for analytics and deep-learning algorithms. In this work, we propose two algorithms that can be applied in the context of a networked multiplayer VR session, to efficiently transmit the displacement and orientation data from the users' hand-based VR HMDs. Moreover, we present a novel method describing effective VR recording of the data exchanged in such a session. Our algorithms, based on the use of dual-quaternions and multivectors, impact the network consumption rate and are highly effective in scenarios involving multiple users. By sending less data over the network and interpolating the in-between frames locally, we manage to obtain better visual results than current state-of-the-art methods. Lastly, we prove that, for recording purposes, storing less data and interpolating them on-demand yields a data set quantitatively close to the original one.

cs.GR↗

arXiv2022

Realistic soft-body tearing under 10ms in VR

We present a novel integration of a real-time continuous tearing algorithm for 3D meshes in VR, suitable for devices of low CPU/GPU specifications, along with a suitable particle decomposition that allows soft-body deformations on both the original and the torn model.

cs.GR↗