Research & Innovation
We deliver services through commercialized knowledge & technology transfer
+10 years of experience in wide array of 3D reseach projects
3D Modeling & Processing
Real-time 3D Graphics
Photorealistic Rendering
Virtual & Augmented Reality
Selected R&D Projects
Manage & execute 3D & AI projects at national and european level
In this challenge we will investigate a machine learning model that can be used to detect objects picked up by the customers from refrigerators using camera images. The problem contains mainly two challenges. The images contain obstructions such as customer's hands and they should be able to run on a Jetson Nano 4Gb, even though they can be trained on a different environment.
This project has indirectly received funding from the European Union’s Horizon 2020 research and innovation programme under project REACH Incubator (Grant Agreement no. 951981).
Selected Publications
Published in high-ranking journals and leading international conferences
Vitsas N., Evangelou I., Papaioannou G. & Gkaravelis A.
Computer Graphics Forum (Proc. of Eurographics 2023)
2023.05 More details
Oriented bounding box (OBB) hierarchies can be used instead of hierarchies based on axis-aligned bounding boxes (AABB), providing tighter fitting to the underlying geometric structures and resulting in improved interference tests, such as ray-geometry intersections. In this paper, we present a method for the fast, parallel transformation of an existing bounding volume hierarchy (BVH), based on AABBs, into a hierarchy based on OBBs. To this end, we parallelise a high-quality OBB extraction algorithm from the literature to operate as a standalone OBB estimator and further extend it to efficiently build an OBB hierarchy in a bottom up manner. This agglomerative approach allows for fast parallel execution and the formation of arbitrary, high-quality OBBs in bounding volume hierarchies. The method is fully implemented on the GPU and extensively evaluated with ray intersections.
The advent of consumer-grade, low-power, untethered virtual reality devices has spurred the creation of numerous applications, with important implications to training, socialisation, education and entertainment. However, such devices are typically based on modified mobile architectures and processing units, offering limited capabilities in terms of geometry and shading throughput, compared to their desktop counterparts. In this work we provide insights on how to implement two combined and particularly challenging tasks on such a platform, those of real-time volume editing and physically-based rendering. We implement and showcase our techniques in the context of a virtual sculpting edutainment application, intended for mass deployment at a virtual reality exhibition centre.
Evangelou I., Vitsas N., Papaioannou G., Georgioudakis M., Chatzisymeon A.
Eurographics Workshop on 3D Object Retrieval (3DOR) 2021, Short Papers
2021.05 More details
The Building Information Modelling (BIM) procedure introduces specifications and data exchange formats widely used by the construction industry to describe functional and geometric elements of building structures in the design, planning, cost estimation and construction phases of large civil engineering projects. In this paper we explain how to apply a modern, low-parameter, neural-network-based classification solution to the automatic geometric BIM element labeling, which is becoming an increasingly important task in software solutions for the construction industry. The network is designed so that it extracts features regarding general shape, scale and aspect ratio of each BIM element and be extremely fast during training and prediction. We evaluate our network architecture on a real BIM dataset and showcase accuracy that is difficult to achieve with a generic 3D shape classification network.
Vitsas N., Gkaravelis A., Vasilakis A. A. & Papaioannou G.
Ray Tracing Gems II: Next Generation Real-Time Rendering with DXR, Vulkan, and OptiX
2021.08 More details
This chapter introduces WebRays, a GPU-accelerated ray intersection engine for the World Wide Web. It aims to offer a flexible and easy-to-use programming interface for robust and high-performance ray intersection tests on modern browsers. We cover design considerations, best practices, and usage examples for several ray tracing tasks.
Vitsas N., Gkaravelis A., Vasilakis A. A., Vardis K. & Papaioannou G.
Eurographics 2020, Education Papers
2020.05 More details
In this paper, we present Rayground; an online, interactive education tool for richer in-class teaching and gradual self-study, which provides a convenient introduction into practical ray tracing through a standard shader-based programming interface. Setting up a basic ray tracing framework via modern graphics APIs, such as DirectX 12 and Vulkan, results in complex and verbose code that can be intimidating even for very competent students. On the other hand, Rayground aims to demystify ray tracing fundamentals, by providing a well-defined WebGL-based programmable graphics pipeline of configurable distinct ray tracing stages coupled with a simple scene description format. An extensive discussion is further offered describing how both undergraduate and postgraduate computer graphics theoretical lectures and laboratory sessions can be enhanced by our work, to achieve a broad understanding of the underlying concepts. Rayground is open, cross-platform, and available to everyone.
Vasilakis A. A., Vardis K. & Papaioannou G.
Eurographics 2020, State-of-the-art Reports
2020.05 More details
In the past few years, advances in graphics hardware have fuelled an explosion of research and development in the field of interactive and real-time rendering in screen space. Following this trend, a rapidly increasing number of applications rely on multifragment rendering solutions to develop visually convincing graphics applications with dynamic content. The main advantage of these approaches is that they encompass additional rasterised geometry, by retaining more information from the fragment sampling domain, thus augmenting the visibility determination stage. With this survey, we provide an overview of and insight into the extensive, yet active research and respective literature on multifragment rendering. We formally present the multifragment rendering pipeline, clearly identifying the construction strategies, the core image operation categories and their mapping to the respective applications. We describe features and trade-offs for each class of techniques, pointing out GPU optimisations and limitations and provide practical recommendations for choosing an appropriate method for each application. Finally, we offer fruitful context for discussion by outlining some existing problems and challenges as well as by presenting opportunities for impactful future research directions.
In this paper we propose an effective technique for the automatic arrangement of spot lights and other luminaires on or near user-provided arbitrary mounting surfaces in order to highlight the geometric details of complex objects. Since potential applications include the lighting design for exhibitions and similar installations, the method takes into account obstructing geometry and potential occlusion from visitors and other non-permanent blocking geometry. Our technique generates the most appropriate position and orientation for light sources based on a local contrast maximization near salient geometric features and a clustering mechanism, producing consistent and view-independent results, with minimal user intervention. We validate our method with realistic test cases including multiple and disjoint exhibits as well as high occlusion scenarios.
Vardis K., Vasilakis A. & Papaioannou G.
High-Performance Graphics 2016, Full Papers
2016.06 More details
We introduce a novel approach to image-space ray tracing ideally suited for the photorealistic synthesis of fully dynamic environments at interactive frame rates. Our method, designed entirely on the rasterization pipeline, alters the acceleration data structure construction from a per-fragment to a per-primitive basis in order to simultaneously support three important, generally conflicting in prior art, objectives: fast construction times, analytic intersection tests and reduced memory requirements. In every frame, our algorithm operates in two stages: A compact representation of the scene geometry is built based on primitive linked-lists, followed by a traversal step that decouples the ray-primitive intersection tests from the illumination calculations; a process inspired by deferred rendering and the path integral formulation of light transport. Efficient empty space skipping is achieved by exploiting several culling optimizations both in xy- and z-space, such as pixel frustum clipping, depth subdivision and lossless buffer down-scaling. An extensive experimental study is finally offered showing that our method advances the area of image-based ray tracing under the constraints posed by arbitrarily complex and animated scenarios.
Collaboration with leading organizations & companies
