Computer Graphics & Visual Computing (CGVC) 2023

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3543876

Browse

Now showing 1 - 20 of 23

Augmenting Anomaly Detection Datasets with Reactive Synthetic Elements
(The Eurographics Association, 2023) Nikolov, Ivan; Vangorp, Peter; Hunter, David
Automatic anomaly detection for surveillance purposes has become an integral part of accident prevention and early warning systems. The lack of sufficient real datasets for training and testing such detectors has pushed a lot of research into synthetic data generation. A hybrid approach by combining real images with synthetic elements has been proven to produce the best training results.We aim to extend this hybrid approach by combining the backgrounds and real people captured in datasets with synthetic elements which dynamically react to real pedestrians and create more coherent video sequences. Our pipeline is the first to directly augment synthetic objects like handbags and suitcases to real pedestrians and provides dynamic occlusion between real and synthetic elements in the images. The pipeline can be easily used to produce a continuous stream of randomized augmented normal and abnormal data for training and testing. As a basis for our augmented images, we use one of the most widely used classical datasets for anomaly detection - the UCSD dataset. We show that the synthetic data produced by our proposed pipeline can be used to make the dataset harder for state-of-the-art models, by introducing more varied and challenging anomalies. We also demonstrate that the additional synthetic normal data can boost the performance of some models. Our solution can be easily extended with additional 3D models, animations, and anomaly scenarios.
AUPE: An Emulator for the ExoMars PanCam Instrument
(The Eurographics Association, 2023) Ladegaard, Ariel; Gunn, Matt; Miles, Helen C.; Tyler, Laurence; Vangorp, Peter; Hunter, David
The European Space Agency's ExoMars mission will be the first European-led planetary rover mission and much preparation and rehearsal is required, both for the personnel involved and the data processing pipelines and analysis software. The long instrument development cycle and significant cost associated with flight hardware prohibits their use for extensive field deployment and testing and so emulator systems are required. For this reason an emulator for the PanCam camera system was developed using commercial off-the-shelf components. PanCam's multispectral imaging capabilities will be used to guide the rover to sites of scientific interest, and development of this emulator and the associated data processing techniques are proving invaluable in ensuring the visual-based data products provided to scientists are accurate and that their processing is a transparent and traceable process.
Automatic Balance Assessment Using Smartphone and AI
(The Eurographics Association, 2023) Sganga, Magalí; Rozmiarek, Patrycja; Ravera, Emiliano; Akanyeti, Otar; Povina, Federico Villagra; Vangorp, Peter; Hunter, David
Postural control assessment is essential for understanding human biomechanics in both static and dynamic situations. The relationship between the center of mass (CoM), center of pressure (CoP), and the base of support (BoS) determines whether a person is capable to maintain the balance. Inertial motion units (IMUs) are portable and cost-effective devices capable of measuring acceleration and angular velocity. The integration of IMUs into smartphones provides an accessible means of evaluating postural control in the general population without the need for expensive and time-consuming laboratory setups. A convolutional neural network (CNN) architecture will be employed to predict the difference between the CoM and CoP behavior during different tasks with data from an optoelectronic motion capture system combined with instrumented treadmill. This study aims to establish the foundation for developing an application that assesses postural control and balance in both healthy and pathological populations.
Automatic Detection of Topological Changes in Geometric Modeling Operations
(The Eurographics Association, 2023) Gaide, Maxime; Marcheix, David; Arnould, Agnès; Skapin, Xavier; Belhaouari, Hakim; Jean, Stéphane; Vangorp, Peter; Hunter, David
Advanced geometric modelers require the detection of topological changes caused by modeling operations such as edge creation, face splitting or volume merging... Such a detection can be dynamically performed by comparing all topological cells (vertices, edges, faces, volumes) before and after each modification, which can be very time consuming. Then, for some events generated in a systematic way, it can also be performed statically before applying each operation, but it entails several hurdles due to the lack of formalization of such events: while some events may seem obvious, others may not appear intuitively or systematically, and this work of defining events needs to be done again for each newly developed operation. In this paper, we propose to formalize the static detection of events and to automate this process based on automatic analysis of operations. To achieve this, we leverage on the formalism of graph transformation rules to describe geometric operations, and on the topological model of G-maps that enables homogeneous modeling of manifold geometric objects in any dimension. The syntactic analysis of rules enables the detection of all events that can be detected statically and also specifies the cells on which events that can only be detected dynamically could occur. With this approach, any new operation can be developed faster within the modeler, ensuring a complete, accurate and automatic event detection.
Classifying User Interface Accessibility for Colourblind Users
(The Eurographics Association, 2023) Jamil, Amaan; Denes, Gyorgy; Vangorp, Peter; Hunter, David
Colour vision deficiency (CVD, colourblindness) is the failure or decreased ability to distinguish between certain colours even under normal lighting conditions. There are an estimated 300 million people worldwide with CVD, with approx. 1 in 12 men (8%) and 1 in 200 women (0.5%)
Computer Graphics and Visual Computing (CGVC): Frontmatter
(The Eurographics Association, 2023) Hunter, David; Peter Vangorp; Vangorp, Peter; Hunter, David
Crafting Visual Narratives: A Case Study on Developing an Engaging Visualisation Poster Using U.S. Immigration Data
(The Eurographics Association, 2023) Ogbonda, Ebube Glory; Butcher, Peter W. S.; Roberts, Jonathan C.; Vangorp, Peter; Hunter, David
This paper presents a design study that elucidates the process of creating an engaging visualisation poster using U.S. immigration data as the focal point. The primary objective is to demonstrate the methodical journey of crafting a compelling story from raw data and effectively portraying it in a poster format. In the process, we manoeuvre through varied tactics of data display, visualisation tool implementation, and poster presentation. As a case study, we offer three important reflective insights that underscore our experience constructing such a poster, which is a practical guide for individuals pursuing similar endeavours. Key considerations underpinning this guide include prioritising a 'big hero' visualisation, ensuring a coherent narrative flow through the poster, and attentively curating the meta information to provide the necessary context, enabling the poster to communicate its message independently.
Differentiable Procedural Models for Single-view 3D Mesh Reconstruction
(The Eurographics Association, 2023) Garifullin, Albert; Maiorov, Nikolay; Frolov, Vladimir; Vangorp, Peter; Hunter, David
Most existing solutions for single-view 3D object reconstruction are based on deep learning with implicit or voxel representations of the scene and are unable to produce detailed and high-quality meshes and textures that can be directly used in practice. Differentiable rendering, on the other hand, is able to produce high-quality meshes but requires several images of an object. We propose a novel approach to single-view 3D reconstruction that uses procedural generator input parameters as a scene representation. Instead of estimating the vertex positions of the mesh directly, we estimate the input parameters of a procedural generator by minimizing the silhouette loss function between reference and rendered images. We use differentiable rendering and create partly differentiable procedural generators to use gradient-based optimization of the loss function. It allows us to create a highly detailed model from a single image taken in an uncontrolled environment. Moreover, the reconstructed model can be further modified in a convenient way by changing the estimated input parameters.
Exploring Language Pedagogy with Virtual Reality and Artificial Intelligence
(The Eurographics Association, 2023) Michael, Brandon; Aburumman, Nadine; Vangorp, Peter; Hunter, David
Virtual Reality (VR) is a highly immersive and interactive experience that renders users to be engrossed in a 3D virtual environment. The recent technological advancements with high-resolution headset display, and accurate tracking of six degrees of freedom paired with controllers allow life-like renditions of real-world scenarios as well as fictional scenarios without potential environmental risks. This paper explores the usage of Virtual Reality in education by incorporating current pedagogical approaches into an interactive 3D virtual environment. The focus of this study revolves around language pedagogy, in specific, the tool developed allows teach users fundamental Mandarin Chinese. This educational VR application enables users to practice their reading and writing skills through a calligraphy lesson and engages users in a listening and speaking lesson through natural conversation. To achieve an organic dialogue, phrases spoken by the user in a lesson are validated immediately through an intuitive phrase recognition system developed using machine learning. The developed prototype has undergone testing to ensure its efficacy. An initial investigation into this prototype found that the majority of participants were supportive of this concept and believe that it would improve the engagement of digital education.
An Image-based Model for 3D Shape Quality Measure
(The Eurographics Association, 2023) Alhamazani, Fahd; Rosin, Paul L.; Lai, Yu-Kun; Vangorp, Peter; Hunter, David
In light of increased research on 3D shapes and the increased processing capability of GPUs, there has been a significant increase in available 3D applications. In many applications, assessment of perceptual quality of 3D shapes is required. Due to the nature of 3D representation, this quality assessment may take various forms. While it is straightforward to measure geometric distortions directly on the 3D shape geometry, such measures are often inconsistent with human perception of quality. In most cases, human viewers tend to perceive 3D shapes from their 2D renderings. It is therefore plausible to measure shape quality using their 2D renderings. In this paper, we present an image-based quality metric for evaluating 3D shape quality given the original and distorted shapes. To provide a good coverage of 3D geometry from different views, we render each shape from 12 equally spaced views, along with a variety of rendering styles to capture different aspects of visual characteristics. Image-based metrics such as SSIM (Structure Similarity Index Measure) are then used to measure the quality of 3D shapes. Our experiments show that by effectively selecting a suitable combination of rendering styles and building a neural network based model, we achieve significantly better prediction for subjective perceptual quality than existing methods.
Immersive WebXR Data Visualisation Tool
(The Eurographics Association, 2023) Ogbonda, Ebube Glory; Vangorp, Peter; Hunter, David
This paper presents a study of a WebXR data visualisation tool designed for the immersive exploration of complex datasets in a 3D environment. The application developed using AFrame, D3.js, and JavaScript enables an interactive, device-agnostic platform compatible with various devices and systems. A user study is proposed to assess the tool's usability, user experience, and mental workload using the NASA Task Load Index (NASA TLX). The evaluation is planned to employ questionnaires, task completion times, and open-ended questions to gather feedback and insights. The anticipated results aim to provide insights into the effectiveness of the application in supporting users in understanding and extracting insights from complex data while delivering an engaging and intuitive experience. Future work will refine and expand the tool's capabilities by exploring interaction guidance, visualisation layout optimisation, and long-term user experience assessment. This research contributes to the growing field of immersive data visualisation and informs future tool design.
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.
Interweaving Data and Stories: A Case Study on Unveiling the Human Dimension of U.S. Refugee Movements through Narrative Visualisation
(The Eurographics Association, 2023) Ogbonda, Ebube Glory; Roberts, Jonathan C.; Butcher, Peter W. S.; Vangorp, Peter; Hunter, David
In response to the escalating global refugee crisis, we present a case-study of developing an advanced tool for interpreting high-dimensional refugee data. Developed using Mapbox and D3.js, our interactive visualisation harmonises geographical and temporal dimensions of U.S. refugee data from the State Department's Refugee Processing Center. Our modular approach and robust data preprocessing enable seamless interactions among diverse visual components. The result is a narrative-driven visualisation that reveals broad immigration trends and individual refugee movements, fostering a nuanced and empathetic understanding of refugee dynamics. This work highlights the power of narrative visualisations in shaping policy decisions and promoting global discourse on the refugee crisis, marking a significant leap in data visualisation for refugee and immigration challenges.
Intra-Model Smoothing Using Depth Aware Multi-Sample Anti-Aliasing for Deferred Rendering Pipelines
(The Eurographics Association, 2023) Magnussen, Birk Martin; Vangorp, Peter; Hunter, David
Subpixel geometry often causes lighting artifacts. In some cases, post-process anti-aliasing algorithms are not sufficiently able to smooth the resulting image. For forward rendering pipelines, multi-sample anti-aliasing is a powerful tool to avoid such artifacts. However, modern rendering pipelines commonly use deferred shading, which causes issues for multi-sample anti-aliasing. This article proposes a new method of combining a pipeline using deferred shading with multi-sample antialiasing while avoiding common pitfalls. The proposed method achieves this by intelligently resolving the geometry buffers with a custom shader based on the depth of samples. This allows the lighting shader to run unchanged on the geometry buffer on a per-fragment basis without additional performance costs. Furthermore, the proposed method is easy to retrofit to existing engines as no changes are required to either the model rendering shader or the deferred lighting shader. The proposed method is demonstrated and implemented on the example of the open-source game engine FreeSpace Open. It is shown that the proposed method is capable of preventing subpixel geometry artifacts, while also avoiding lighting artifacts from resolving geometry buffers and avoiding the performance overhead of calculating lighting per sample.
Investigating Deep Learning for Identification of Crabs and Lobsters on Fishing Boats
(The Eurographics Association, 2023) Iftikhar, Muhammad; Tiddeman, Bernard; Neal, Marie; Hold, Natalie; Neal, Mark; Vangorp, Peter; Hunter, David
This paper describes a collaboration between marine and computer scientists to improve fisheries data collection. We evaluate deep learning (DL)-based solutions for identifying crabs and lobsters onboard fishing boats. A custom made electronic camera systems onboard the fishing boats captures the video clips. An automated process of frame extraction is adopted to collect images of crabs and lobsters for training and evaluating DL networks. We train Faster R-CNN, Single Shot Detector (SSD), and You Only Look Once (YOLO) with multiple backbones and input sizes. We also evaluate the efficiency of lightweight models for low-power devices equipped on fishing boats and compare the results of MobileNet-based SSD and YOLO-tiny versions. The models trained with higher input sizes result in lower frames per second (FPS) and vice versa. Base models are more accurate but compromise computational and run time cost. Lighter versions are flexible to install with lower mAP than full models. The pre-trained weights for training models on new datasets have a negligible impact on the results. YOLOv4-tiny is a balanced trade-off between accuracy and speed for object detection for low power devices that is the main step of our proposed pipeline for automated recognition and measurement of crabs and lobsters on fishing boats.
Just Noticeable Difference of Dead Pixels in Monochrome Computer-Generated Holograms
(The Eurographics Association, 2023) Lindfield, Nicholas; Carey, Remington; Hulusic, Vedad; Milne, Darran; Tang, Wen; Vangorp, Peter; Hunter, David
Computer-generated holography (CGH) is a method for replicating scenes that incorporates depth, making them potentially much more realistic than traditional displays. Because CGH uses diffractive optics to generate scenes, holograms are also significantly more robust against dead pixels: while a single dead pixel is often noticeable in traditional displays, in holography much higher numbers are needed before a viewer realises the issue. This work is a pilot study to determine the Just Noticeable Difference of the number of dead pixels of a hologram, i.e., the minimum amount that need to be added before a viewer notices the difference. From these JNDs a quality ruler will be generated, which later work will use to compare the impact of other distortions on the perceived quality of a hologram. Results thus far suggest an addition of 4% dead pixels is required to notice a difference, which is significantly greater than the tolerance observed for traditional displays, where the fault class threshold is less than 0.05%.
Less is more: Focused Design and Problem Framing in Visualisation - Developing the ColloCaid Collocation Editor
(The Eurographics Association, 2023) Roberts, Jonathan C.; Butcher, Peter W. S.; Rees, Geraint; Lew, Robert; Sharma, Nirwan; Frankenberg-Garcia, Anna; Vangorp, Peter; Hunter, David
One of the challenges when developing a visualisation tool, especially at the start of a research project, is to amalgamate numerous requirements and various possibilities and decide what to create. With software development, it is too easy to incorporate all ideas, but quickly the tool becomes unusable, with feature overload. We reflect on designing and building the ColloCaid collocation visualisation editor, especially our conceptual focus on simplicity. We were inspired by Hemingway's iceberg theory of deliberate omission, to help frame the visualisation challenge and achieve clarity and focused design. The ColloCaid tool enables people to discover collocations, to help people improve vocabulary and fluency as they write. It was developed by a multidisciplinary team of applied linguists, lexicographers, human-computer interaction and visualisation experts. We promote focused design and problem solving, in visualisation, highlight concepts, including parti, design essence, and simplification. We provide a collection of insights that hold potential to evolve into a structured set of design guidelines, offering valuable direction to researchers.
Model Reevaluation Based on Graph Transformation Rules
(The Eurographics Association, 2023) Gaide, Maxime; Marcheix, David; Arnould, Agnès; Skapin, Xavier; Belhaouari, Hakim; Jean, Stéphane; Vangorp, Peter; Hunter, David
In this paper, we extend the scope of naming problem studies to encompass rule-based graph transformation modeling systems. We propose a novel persistent naming method that capitalizes on the formalized operations of generalized maps and graph transformation rules. It enables a unique and homogeneous characterisation of entities across all dimensions.
RPS-Net: Indoor Scene Point Cloud Completion using RBF-Point Sparse Convolution
(The Eurographics Association, 2023) Wang, Tao; Wu, Jing; Ji, Ze; Lai, Yu-Kun; Vangorp, Peter; Hunter, David
We introduce a novel approach to the completion of 3D scenes, which is a practically important task as captured point clouds of 3D scenes tend to be incomplete due to limited sensor range and occlusion. We address this problem by utilising sparse convolutions, commonly used for recognition tasks, to this content generation task, which can well capture the spatial relationships while ensuring high efficiency, as only samples near the surface need to be processed. Moreover, traditional sparse convolutions only consider grid occupancies, which cannot accurately locate surface points, with unavoidable quantisation errors. Observing that local surface patches have common patterns, we propose to sample a Radial Basis Function (RBF) field within each grid which is then compactly represented using a Point Encoder-Decoder (PED) network. This further provides a compact and effective representation for 3D completion, and the decoded latent feature includes important information of the local area of the point cloud for more accurate, sub-voxel level completion. Extensive experiments demonstrate that our method outperforms state-of-the-art methods by a large margin.
Strategies for More Energy Efficient Volume Analysis and Direct Volume Rendering Descriptor Computation
(The Eurographics Association, 2023) Hauenstein, Jacob D.; Newman, Timothy S.; Vangorp, Peter; Hunter, David
A study of energy use (in an x86-class environment) for computation of descriptors used in analysis and in one common scientific visualisation strategy, direct volume rendering (DVR), of volumetric data is presented. Focus is on descriptors used by classic ray-casting-based DVR, including gradients and curvature. Modified computational strategies are considered versus standard approaches on x86. The modified strategies explored include two memory-based ones and four computation-based ones. Use of energy-optimal strategies was able to achieve close to 20% energy savings for gradient descriptor determination. Factor-of-two improvement in energy efficiency for curvature descriptor determination was achieved through these strategies.

Browse

Browsing Computer Graphics & Visual Computing (CGVC) 2023 by Title

Results Per Page

Sort Options