Search Results

Now showing 1 - 10 of 41
  • Item
    Recreational Motion Simulation: A New Frontier for Virtual Worlds Research
    (The Eurographics Association, 2021) Williams, Benjamin; Headleand, Christopher J.; Xu, Kai and Turner, Martin
    Motion simulation is a developing field which continues to grow with the recent incline in commercial virtual reality. Whilst the majority of motion simulation research focuses on flight simulation and training, its utility in recreational settings is often overlooked. Despite this lack of research, the use of motion simulators for recreational purposes spans decades, and is still today one of the most popular applications of motion simulator devices. Furthermore, with the recent development of low-cost motion simulation platforms, consumers have begun to use these devices in the home. Research regarding motion simulation and its effects in recreational experiences is needed now more than ever, and in this position paper we outline several reasons for its importance.
  • Item
    Recognising Specific Foods in MRI Scans Using CNN and Visualisation
    (The Eurographics Association, 2020) Gardner, Joshua; Al-Maliki, Shatha; Lutton, Évelyne; Boué, François; Vidal, Franck; Ritsos, Panagiotis D. and Xu, Kai
    This work is part of an experimental project aiming at understanding the kinetics of human gastric emptying. For this purpose magnetic resonance imaging (MRI) images of the stomach of healthy volunteers have been acquired using a state-of-art scanner with an adapted protocol. The challenge is to follow the stomach content (food) in the data. Frozen garden peas and petits pois have been chosen as experimental proof-of-concept as their shapes are well defined and are not altered in the early stages of digestion. The food recognition is performed as a binary classification implemented using a deep convolutional neural network (CNN). Input hyperparameters, here image size and number of epochs, were exhaustively evaluated to identify the combination of parameters that produces the best classification. The results have been analysed using interactive visualisation. We prove in this paper that advances in computer vision and machine learning can be deployed to automatically label the content of the stomach even when the amount of training data is low and the data imbalanced. Interactive visualisation helps identify the most effective combinations of hyperparameters to maximise accuracy, precision, recall and F1 score, leaving the end-user evaluate the possible trade-off between these metrics. Food recognition in MRI scans through neural network produced an accuracy of 0.97, precision of 0.91, recall of 0.86 and F1 score of 0.89, all close to 1.
  • Item
    Inpainting Normal Maps for Lightstage data
    (The Eurographics Association, 2023) Zuo, Hancheng; Tiddeman, Bernard; Vangorp, Peter; Hunter, David
    This paper presents a new method for inpainting of normal maps using a generative adversarial network (GAN) model. Normal maps can be acquired from a lightstage, and when used for performance capture, there is a risk of areas of the face being obscured by the movement (e.g. by arms, hair or props). Inpainting aims to fill missing areas of an image with plausible data. This work builds on previous work for general image inpainting, using a bow tie-like generator network and a discriminator network, and alternating training of the generator and discriminator. The generator tries to sythesise images that match the ground truth, and that can also fool the discriminator that is classifying real vs processed images. The discriminator is occasionally retrained to improve its performance at identifying the processed images. In addition, our method takes into account the nature of the normal map data, and so requires modification to the loss function. We replace a mean squared error loss with a cosine loss when training the generator. Due to the small amount of available training data available, even when using synthetic datasets, we require significant augmentation, which also needs to take account of the particular nature of the input data. Image flipping and in-plane rotations need to properly flip and rotate the normal vectors. During training, we monitored key performance metrics including average loss, Structural Similarity Index Measure (SSIM), and Peak Signal-to-Noise Ratio (PSNR) of the generator, alongside average loss and accuracy of the discriminator. Our analysis reveals that the proposed model generates high-quality, realistic inpainted normal maps, demonstrating the potential for application to performance capture. The results of this investigation provide a baseline on which future researchers could build with more advanced networks and comparison with inpainting of the source images used to generate the normal maps.
  • Item
    Medical Ultrasound Training in Virtual Reality
    (The Eurographics Association, 2020) Elliman, James P.; Bethapudi, Sarath; Koulieris, George Alex; Ritsos, Panagiotis D. and Xu, Kai
    In this work we propose a novel training solution for learning and practising the core psychomotor skills required in Diagnostic Ultrasound examinations with a computer-based simulator. This is in response to the long-standing challenges faced by educators in providing regular training opportunities as a shortage of equipment, staff unavailability and cost, hamper the current training model. We propose an alternative, VR-based model with a highly realistic 3D environment. To further realism of the experience, 3D printed props that work in conjunction with the simulation software will be designed. Our approach further extends previous work in generative model-based US simulation by developing a ray-tracing algorithm for use with the recently released NVidia RTX technology.
  • Item
    Using The Barnes-Hut Approximation for Fast N-Body Simulations in Computer Graphics
    (The Eurographics Association, 2023) Dravecky, Peter; Stephenson, Ian; Vangorp, Peter; Hunter, David
    Particle systems in CG often encounter performance issues when all the particles rely on mutual influence, producing an O(N2) performance. The Barnes-Hut approximation is used in the field of astrophysics to provide sufficiently accurate results in O(Nlog(N)) time. Here we explore a hardware accelerated implementation of this algorithm, implemented within SideFX Houdini - the commercial tool typically used for particle work in film. We are able to demonstrate a workflow with integrates into the existing artist friendly environment, with performance improved by orders of magnitudes for typically large simulations, and negligible visual change in results.
  • Item
    Projectional Radiography Simulator: an Interactive Teaching Tool
    (The Eurographics Association, 2019) Sujar, Aaron; Kelly, Graham; García, Marcos; Vidal, Franck; Vidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.
    Radiographers need to know a broad range of knowledge about X-ray radiography, which can be specific to each part of the body. Due to the harmfulness of the ionising radiation used, teaching and training using real patients is not ethical. Students have limited access to real X-ray rooms and anatomic phantoms during their studies. Books, and now web apps, containing a set of static pictures are then often used to illustrate clinical cases. In this study, we have built an Interactive X-ray Projectional Simulator using a deformation algorithm with a real-time X-ray image simulator. Users can load various anatomic models and the tool enables virtual model positioning in order to set a specific position and see the corresponding X-ray image. It allows teachers to simulate any particular X-ray projection in a lecturing environment without using real patients and avoiding any kind of radiation risk. This tool also allows the students to reproduce the important parameters of a real X-ray machine in a safe environment. We have performed a face and content validation in which our tool proves to be realistic (72% of the participants agreed that the simulations are visually realistic), useful (67%) and suitable (78%) for teaching X-ray radiography.
  • Item
    Optimising Underwater Environments for Mobile VR
    (The Eurographics Association, 2019) Cenydd, Llyr ap; Headleand, Christopher; Vidal, Franck P. and Tam, Gary K. L. and Roberts, Jonathan C.
    Mobile Virtual Reality (VR) has advanced considerably in the last few years, driven by advances in smartphone technology. There are now a number of commercial offerings available, from smartphone powered headsets to standalone units with full positional tracking. Similarly best practices in VR have matured quickly, facilitating comfortable and immersive VR experiences. There remains however many optimisation challenges when working with these devices, as while the need to render at high frame rates is universal, the hardware is limited by both computational power and battery capacity. There is also often a requirement that apps run smoothly across a wide variety of headsets. In this paper, we describe lessons learned in rendering and optimising underwater environments for mobile VR, based on our experience developing the popular aquatic safari application 'Ocean Rift'. We start by analyzing essential best practices for mobile app development, before describing low-cost techniques for creating immersive underwater environments. While some techniques discussed are universal to modern mobile VR development, we also consider issues that are unique to underwater applications.
  • Item
    Improving Ray Tracing Performance with Variable Rate Shading
    (The Eurographics Association, 2021) Dahlin, Alexander; Sundstedt, Veronica; Xu, Kai and Turner, Martin
    Hardware-accelerated ray tracing has enabled ray traced reflections for real-time applications such as games. However, the number of traced rays during each frame must be kept low to achieve expected frame rates. Therefore, techniques such as rendering the reflections at quarter resolution are used to limit the number of rays. The recent hardware features inline ray tracing, and variable rate shading (VRS) could be combined to limit the number of rays even further. This research aims to use hardware VRS to limit the number of rays while maintaining the visual quality in the final rendered image. An experiment with performance tests is performed on a rendering pipeline using different techniques to generate rays. The techniques use inline ray tracing combined with VRS and ray generation shaders. These are compared and evaluated using performance tests and the image evaluator FLIP. The results show that limiting the number of rays with hardware VRS leads to improved performance while the difference in visual quality remains comparable.
  • Item
    Where's Wally? A Machine Learning Approach
    (The Eurographics Association, 2021) Barthelmes, Tobias; Vidal, Franck; Xu, Kai and Turner, Martin
    Object detection has been implemented in all sorts of real-life scenarios such as facial recognition, traffic monitoring and medical imaging but the research that has gone into object detection in drawings and cartoons is not nearly as extensive. The Where's Wally puzzle books give a good opportunity to implement some of these real-life methods into the fictional world. The Wally detection framework proposed is composed of two stages: i) a Haar-cascade classifier based on the Viola-Jones framework, which detects possible candidates from a scenario from the Where'sWally books, and ii) a lightweight convolutional neural network (CNN) that re-labels the objects detected by the cascade classifier. The cascade classifier was trained on 85 positive images and 172 negative images. It was then applied to 12 test images, which produced over 400 false positives. To increase the accuracy of the models, hard negative mining was implemented. The framework achieved a recall score of 84.61% and an F1 score of 78.54%. Improvements could be made to the training data or the CNN to further increase these scores.
  • Item
    CLAWS: Computational Load Balancing for Accelerated Neighbor Processing on GPUs using Warp Scheduling
    (The Eurographics Association, 2020) Gross, Julian; Köster, Marcel; Krüger, Antonio; Ritsos, Panagiotis D. and Xu, Kai
    Nearest neighbor search algorithms on GPUs have been improving for years. Starting with tree-based approaches in the middle 70's, state-of-the-art methods use hash-based or grid-based methods. Leveraging high-performance hardware functionality decreases runtime of these search algorithms. Furthermore, memory consumption has been decreased significantly as well using Shared Memory. In the scope of these enhancements, particles have been reordered by different constraints that simplify neighbor processing. However, inspecting the existing algorithms reveals underused capabilities caused by algorithm desing. Exploiting these capabilities in a smart way can increase occupancy and efficiency on GPUs. In this paper, we present a neighbor processing approach that is based on dynamic load balancing. We rely on a lightweight workload-analysis phase that is applied during neighbor processing to distribute work throughout all warps in a thread group on-the-fly. In different domains, the neighbor function is often symmetric and, thus, commutative in each argument. In contrast to prior work, we use this domain knowledge to reduce the number of memory accesses considerably. Measurements of the newly introduced features on our evaluation scenarios show a comparable runtime performance to state-of-the-art methods. Increasing the overall workload by processing million-particle domains leads to significant improvements in terms of runtime. At the same time, we minimize global memory consumption to enable more particles to be processed compared to current approaches.