Computer Graphics & Visual Computing (CGVC) 2024

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607040

Browse

Now showing 1 - 20 of 29

Authoring Visualisation of Routinely Collected Data Using LLMs
(The Eurographics Association, 2024) Hosseini, Amir; Wood, Jo; Elshehaly, Mai; Hunter, David; Slingsby, Aidan
The integration of routinely collected healthcare data into decision-making processes has the potential to revolutionise patient care and health outcomes. However, the complexity and heterogeneity of these datasets pose significant challenges for effective querying and analysis. Visualisation supports socio-technical processes where data analytics are augmented with human expertise to overcome data complexity. However, the authorship of effective visualisation is a challenging task, especially for users without a technical background, such as commissioners, clinicians and population health experts. This complexity calls for more efforts to develop natural language interfaces (NLIs) to democratise access to and understanding of routine data through visualisation. This short paper presents an innovative approach utilising Large Language Models (LLMs) to facilitate the querying and visualisation of routinely collected healthcare data. We present a preliminary framework for combining natural language queries with visualisation recommendation systems to retrieve and visualise relevant information from electronic health records (EHRs). We propose a human-in-the-loop approach for establishing accurate and efficient LLM-enabled information retrieval. Our preliminary findings suggest that LLMs can significantly streamline the visualisation authoring process, enabling stakeholders and healthcare professionals to access critical information rapidly and accurately. This work underscores the potential of LLM-driven solutions in advancing healthcare data utilisation and paves the way for future research in this promising intersection of artificial intelligence and medical informatics.
EBBVH: A Novel Method for Constructing Bounding Volume Hierarchies
(The Eurographics Association, 2024) Houghton, Matthew; Spoerer, Kristian; Hunter, David; Slingsby, Aidan
We present an attempt to improve upon the construction of the most prevalent acceleration structure that is used in ray traced rendering techniques, the Bounding Volume Hierarchy. Our improvement is a novel technique for BVH construction called 'Edge-Based Bounding Volume Hierarchy'. This algorithm uses a hybrid top-down & bottom-up approach to improve performance for raytracing in large scenes, by up to 10x in some scenes.
Map Augmentation and Sketching for Cycling Experience Elicitation
(The Eurographics Association, 2024) Reljan-Delaney, Mirela; Wood, Jo D.; Taylor, Alex S.; Hunter, David; Slingsby, Aidan
This work examines the use of maps for knowledge elicitation in the sphere of urban cycling. The study involved running 14 distinct workshops, each serving as a unique data collection session for a particular individual. In each workshop, the participant was provided with 12 different renditions of the geographical areas as well as drawing materials. The geographical area renditions contained regions specified by the participant as cycling locations during the preparatory correspondence. The outputs were analysed for patterns in map augmentations and thematic content in the sketches. We have found that participants engaged deeply with the map augmentation process expressing their preferences and giving new insights. Themes such as connectivity, scenic beauty, and temporality emerged prominently from the analysed data, shedding light on the subjective experiences and preferences of urban cyclists.
Skipping Spheres: SDF Scaling & Early Ray Termination for Fast Sphere Tracing
(The Eurographics Association, 2024) Polychronakis, Andreas; Koulieris, George Alex; Mania, Katerina; Hunter, David; Slingsby, Aidan
This paper presents a rapid rendering pipeline for sphere tracing Signed Distance Functions (SDFs), showcasing a notable boost in performance compared to the current state-of-the-art. Existing methods endeavor to reduce the ray step count by adjusting step size using heuristics or by rendering multiple intermediate lower-resolution buffers to pre-calculate non-salient pixels at reduced quality. However, the accelerated performance with low-resolution buffers often introduces artifacts compared to fully sphere-traced scenes, especially for smaller features, which might go unnoticed altogether. Our approach significantly reduces steps compared to prior work while minimising artifacts. We accomplish this based on two key observations and by employing a single low-resolution buffer: Firstly, we perform SDF scaling in the low-resolution buffer, effectively enlarging the footprint of the implicit surfaces when rendered in low resolution, ensuring visibility of all SDFs. Secondly, leveraging the low-resolution buffer rendering, we detect when a ray converges to high-cost surface edges and can terminate sphere tracing earlier than usual, further reducing step count. Our method achieves a substantial performance improvement (exceeding 3× in certain scenes) compared to previous approaches, while minimizing artifacts, as demonstrated in our visual fidelity evaluation.
Real-time Data-Oriented Virtual Forestry Simulation for Games
(The Eurographics Association, 2024) Williams, Benjamin; Oliver, Tom; Ward, Davin; Headleand, Chris; Hunter, David; Slingsby, Aidan
The current frontier of virtual forestry algorithms remain largely unoptimised and ultimately unsuitable for real-time applications. Providing an optimisation strategy for the real-time simulation of virtual forestry would find particular utility in some areas, for example, in video games. With this motivation in mind, this paper presents a novel optimisation strategy for asymmetric plant competition models. In our approach, we utilise a data-oriented methodology with spatial hashing to enable the real-time simulation of virtual forests. Our approach also provides a significant improvement in performance when contrasted with existing serial implementations. Furthermore, we find that the introduction of our optimisation strategy can be used to simulate hundreds of thousands of virtual trees, in real-time, on a typical desktop machine.
Creating Data Art: Authentic Learning and Visualisation Exhibition
(The Eurographics Association, 2024) Roberts, Jonathan C.; Hunter, David; Slingsby, Aidan
We present an authentic learning task designed for computing students, centred on the creation of data-art visualisations from chosen datasets for a public exhibition. This exhibition was showcased in the cinema foyer for two weeks in June, providing a real-world platform for students to display their work. Over the course of two years, we implemented this active learning task with two different cohorts of students. In this paper, we share our experiences and insights from these activities, highlighting the impact on student engagement and learning outcomes. We also provide a detailed description of the seven individual tasks that learners must perform: topic and data selection and analysis, research and art inspiration, design conceptualisation, proposed solution, visualisation creation, exhibition curation, and reflection. By integrating these tasks, students not only develop technical skills but also gain practical experience in presenting their work to a public audience, bridging the gap between academic learning and professional practice.
Computer Graphics and Visual Computing (CGVC): Frontmatter
(The Eurographics Association, 2024) Slingsby, Aidan; Hunter, David; Slingsby, Aidan; Hunter, David
The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others
(The Eurographics Association, 2024) Sikar, Daniel; Garcez, Artur d'Avila; Bloomfield, Robin; Weyde, Tillman; Peeroo, Kaleem; Singh, Naman; Hutchinson, Maeve; Laksono, Dany; Reljan-Delaney, Mirela; Hunter, David; Slingsby, Aidan
This study introduces the Misclassification Likelihood Matrix (MLM) as a novel tool for quantifying the reliability of neural network predictions under distribution shifts. The MLM is obtained by leveraging softmax outputs and clustering techniques to measure the distances between the predictions of a trained neural network and class centroids. By analyzing these distances, the MLM provides a comprehensive view of the model's misclassification tendencies, enabling decision-makers to identify the most common and critical sources of errors. The MLM allows for the prioritization of model improvements and the establishment of decision thresholds based on acceptable risk levels. The approach is evaluated on the MNIST dataset using a Convolutional Neural Network (CNN) and a perturbed version of the dataset to simulate distribution shifts. The results demonstrate the effectiveness of the MLM in assessing the reliability of predictions and highlight its potential in enhancing the interpretability and risk mitigation capabilities of neural networks. The implications of this work extend beyond image classification, with ongoing applications in autonomous systems, such as self-driving cars, to improve the safety and reliability of decision-making in complex, real-world environments.
A Stereo-Integrated Novel View Synthesis Pipeline for the Enhancement of Road Surface Reconstruction Dataset
(The Eurographics Association, 2024) Zhan, Mochuan; Morley, Terence; Turner, Martin; Hunter, David; Slingsby, Aidan
This proposal outlines a novel view synthesis pipeline designed for road reconstruction in autonomous driving scenarios that leverages virtual camera technology to synthesise images from unvisited camera poses, thereby enhancing and expanding current datasets. It consists of three main steps: data acquisition, data preprocessing and fusion, and then importantly interacting with new 3D view synthesis with geometric priors. The modular design allows each component to be independently optimised and upgraded, ensuring flexibility and adaptability to various datasets and task requirements. The proposed approach aims to improve the robustness, realism, and photometric consistency of novel view synthesis, effectively handling dynamic scenes and varying lighting conditions. Additionally, this research plans to open-source a low-cost stereo camera hardware solution with the included software implementation.
DeFT-Net: Dual-Window Extended Frequency Transformer for Rhythmic Motion Prediction
(The Eurographics Association, 2024) Ademola, Adeyemi; Sinclair, David; Koniaris, Babis; Hannah, Samantha; Mitchell, Kenny; Hunter, David; Slingsby, Aidan
Enabling online virtual reality (VR) users to dance and move in a way that mirrors the real-world necessitates improvements in the accuracy of predicting human motion sequences paving way for an immersive and connected experience. However, the drawbacks of latency in networked motion tracking present a critical detriment in creating a sense of complete engagement, requiring prediction for online synchronization of remote motions. To address this challenge, we propose a novel approach that leverages a synthetically generated dataset based on supervised foot anchor placement timings of rhythmic motions to ensure periodicity resulting in reduced prediction error. Specifically, our model compromises a discrete cosine transform (DCT) to encode motion, refine high frequencies and smooth motion sequences and prevent jittery motions. We introduce a feed-forward attention mechanism to learn based on dual-window pairs of 3D key points pose histories to predict future motions. Quantitative and qualitative experiments validating on the Human3.6m dataset result in observed improvements in the MPJPE evaluation metrics protocol compared with prior state-of-the-art.
Assessing the Reliability of Integrated Gradients-Based Saliency Maps for 3D Point Cloud Semantic Segmentation Models
(The Eurographics Association, 2024) Ciprián-Sánchez, Jorge F.; Burmeister, Josafat-Mattias; Cech, Tim; Richter, Rico; Döllner, Jürgen; Hunter, David; Slingsby, Aidan
Deep learning models achieve high accuracy in the semantic segmentation of 3D point clouds; however, it is challenging to discern which patterns a model has learned and how it derives its output from the input. Recently, the Integrated Gradients method has been adopted to explain semantic segmentation models for 3D point clouds. This method can be used to generate saliency maps that visualize the contribution of input points to a particular model output. However, there is a lack of quantitative evaluation of the reliability of the generated saliency maps and the influence of the baseline selection (a central component of Integrated Gradients) on the method's results. In this paper, we quantitatively evaluate the reliability of saliency maps generated by the Integrated Gradients method for a 3D point cloud semantic segmentation model through well-known sanity checks from the image domain that we adapt to 3D point cloud segmentation. We perform these sanity checks for three different baselines to further evaluate the stability of the generated saliency maps concerning the baseline choice. Our results indicate that the Integrated Gradients method is sensitive to both the parameters of the model and training labels, unstable concerning the choice of baseline, and that, although it can identify points with high contributions to the model output, it fails to identify correctly if such contributions are positive or negative. Finally, we propose an averaging approach to aggregate the results of points that receive multiple scores from Integrated Gradients during the segmentation process and show that it produces saliency maps that better reflect high-contribution input points than previous approaches.
Min-Max Modifiable Nested Octrees M3NO: Indexing Point Clouds with Arbitrary Attributes in Real Time
(The Eurographics Association, 2024) Hermann, Paul; Krämer, Michel; Dorra, Tobias; Kuijper, Arjan; Hunter, David; Slingsby, Aidan
We present a data structure that allows 3D point clouds with arbitrary attributes to be indexed in real time. We focus on large datsets from mobile mapping systems such as airborne and terrestrial laser scanners. Compared to traditional indexing approaches running offline, our data structure can be created incrementally while the points are being recorded. This allows the data to be used (i.e. analyzed or visualized) already during acquisition or immediately after it has finished. The data structure enables queries based on spatial extent and value ranges of arbitrary attributes. This is in contrast to existing works, which focus on either spatial or attribute indexing, typically are not real-time capable, or only support a limited set of attributes. Our approach combines Modifiable Nested Octrees and extended Binned Min-Max Octrees. Using a subset of the well known AHN4 dataset with 138 million points, we evaluate the approach, assess quality and query performance, and compare it with an existing state-of-the-art solution. On commodity hardware, our data structure can process 1.97 million points per second, which is more than most commercially available laser scanners can record. When filtering points by attribute value ranges, it also reduces the number of octree nodes that have to be loaded, and it substantially outperforms naive sequential point filtering.
Comparing Distance Metrics in Space-time Clustering to Provide Visual Summaries of Traffic Congestion
(The Eurographics Association, 2024) Baudains, Peter; Holliman, Nicolas S.; Hunter, David; Slingsby, Aidan
Smart Cities are characterised by their ability to collect and process large volumes of sensor data. Visual analytics is then often required to make this data actionable and to allow decisions to be made in support of the well-being of inhabitants. In this study, using Bus Open Data, we consider how space-time clustering can be used to generate visual summaries of traffic congestion. Using a space-time extension of DBSCAN, our clustering procedure is evaluated with respect to both Euclidean distance and street network distance. Results show that network-based distance metrics improve the clustering procedure by generating clusters with less uncertainty. Moreover, congestion clusters derived from network-based distances are also more likely to last longer and to precede future congestion appearing nearby. We suggest that network-based distances might provide greater opportunity for more impactful traffic control room decision-making and we discuss steps towards a near real-time system design that can be used in support of operational decision-making.
Semantic UV Mapping to Improve Texture Inpainting for 3D Scanned Indoor Scenes
(The Eurographics Association, 2024) Vermandere, Jelle; Bassier, Maarten; Cuypers, Suzanna; Vergauwen, Maarten; Hunter, David; Slingsby, Aidan
This work aims to improve texture inpainting following clutter removal in scanned indoor meshes. This is achieved through a new UV mapping pre-processing step that leverages semantic information from indoor scenes to more accurately align the UV islands with the 3D representations of distinct structural elements, such as walls and floors. Semantic UV Mapping enhances traditional UV unwrapping algorithms by incorporating not only geometric features but also visual features derived from the existing texture. This segmentation improves UV mapping and simultaneously simplifies the 3D geometric reconstruction of the scene after the removal of loose objects. Each segmented element can then be reconstructed separately, using the boundary conditions of the adjacent elements. Since this is performed as a pre-processing step, other specialized methods for geometric and texture reconstruction can be employed in the future to further enhance the results.
Does Empirical Evidence from Healthy Aging Studies Predict a Practical Difference Between Visualizations for Different Age Groups?
(The Eurographics Association, 2024) Shao, Shan; Li, Yiran; Meso, Andrew I.; Holliman, Nicolas S.; Hunter, David; Slingsby, Aidan
When communicating critical information to decision-makers, one of the major challenges in visualization is whether the communication is affected by different perceptual or cognitive abilities, one major influencing factor is age. We review both visualization and psychophysics literature to understand where quantitative evidence exists on age differences in visual perception. Using contrast sensitivity data from the literature we show how the differences between visualizations for different age groups can be predicted using a new model of visible frequency range with age. The model assumed that at threshold values some visual data will not be visible to older people (spatial frequency > 2 and contrast <=0.01). We apply this result to a practical visualization and show an example that at higher levels of contrast, the visual signal should be perceivable by all viewers over 20. Universally usable visualization should use a contrast of 0.02 or higher and be designed to avoid spatial frequencies greater than eight cycles per degree to accommodate all ages. There remains much research to do on to translate psychophysics results to practical quantitative guidelines for visualization producers.
Visual Interpretation of Tagging: Advancing Understanding in Task-Oriented Dialogue Systems
(The Eurographics Association, 2024) Zhou, Yazhuo; Xing, Yiwen; Abdul-Rahman, Alfie; Borgo, Rita; Hunter, David; Slingsby, Aidan
In task-oriented dialogue systems, tagging tasks leverage Large Language Models (LLMs) to understand dialogue semantics. The specifics of how these models capture and utilize dialogue semantics for decision-making remain unclear. Unlike binary or multi-classification, tagging involves complex multi-to-multi relationships between features and predictions, complicating attribution analyses. To address these challenges, we introduce a novel interactive visualization system that enhances understanding of dialogue semantics through attribution analysis. Our system offers a multi-level and layer-wise visualization framework, revealing the evolution of attributions across layers and allowing users to interactively probe attributions. With a dual-view for streamlined comparisons, users can effectively compare different LLMs. We demonstrate our system's effectiveness with a common task-oriented dialogue task: slot filling. This tool aids NLP experts in understanding attributions, diagnosing models, and advancing dialogue understanding development by identifying potential sources of model hallucinations.
Reflections on the Evolution of the BookTracker Visualization Platform
(The Eurographics Association, 2024) Xing, Yiwen; Dondi, Cristina; Borgo, Rita; Abdul-Rahman, Alfie; Hunter, David; Slingsby, Aidan
Understanding the trade data of historical books is crucial for researchers investigating the distribution and provenance of Incunabula (books printed between 1450 and 1500). We incrementally developed BookTracker, a platform featuring multiple visualization and visual analytics applications to support these research efforts. This platform leverages data from the Material Evidence in Incunabula (MEI) database, which meticulously records detailed information on the provenance, ownership, and use of 15th-century printed books. BookTracker began with a focus on providing visualization and visual analytical solutions to effectively present each book provenance's chronological and geographical information. Through three years of collaborative work with domain experts, we continually explored the Material Evidence in Incunabula (MEI) data and discovered more possibilities for visualization to represent this rich information. Gradually, a suite of specialized visualization tools for specific analytical purposes was developed, including DanteSearchVis, DanteExploreVis, KURF2022, KURF2023, and OwnershipTracker. These tools now comprise the BookTracker platform, which has evolved to explore various features and aspects of the data. This paper details the evolution of BookTracker's design and development alongside domain experts, highlighting the reflections and lessons learned from its application in various research projects. We discuss this long-term collaborative visualization project, hoping to offer our experience as a case study for similar research in the future.
Multi-level Visualization for Exploration of Structures in Missing Data
(The Eurographics Association, 2024) Alsufyani, Sarah; Forshaw, Matthew; Din, Silvia Del; Yarnall, Alison; Rochester, Lynn; Fernstad, Sara Johansson; Hunter, David; Slingsby, Aidan
Missing data refers to the absence of a value in the dataset where it was expected to be present. This absence is common across various fields. It can be caused by a range of factors in the data collection process, and may severely impact analysis through unreliable or biased results. Missing data visualization provides an effective approach to exploring the missing data, recognizing the missingness patterns and structures, and determining optimal solutions through interactive visual interfaces. This paper presents a visualization prototype that incorporates two novel techniques, the MissVisG glyph and the MissVis plot, to support the exploration of missing values in data. The visualization provides an overview of missing values, and helps identify patterns in the data to guide users in selecting appropriate methods for dealing with the missingness. A multi-step evaluation process is utilized to assess and ensure the usability and effectiveness of the visualization.
Visualizing Complex Data Decisions: Design Study for Ethical Factors in AI Clinical Decision Support Systems
(The Eurographics Association, 2024) Surodina, Svitlana; Volkova, Daria; Abdul-Rahman, Alfie; Borgo, Rita; Hunter, David; Slingsby, Aidan
Despite the proliferation of Artificial Intelligence (AI) technologies, their uptake in clinical settings has been lacking progress due to complexities of sociotechnical factors and intricacies of decision-making. Fairness and bias of predictive models, ethics and quality of training data, and corresponding compliance requirements become especially pressing while remaining fuzzy and implicit for various stakeholders who make the decisions. We present learnings and future directions from a design study with domain experts and propose a novel approach to encoding and collaborative reasoning on complex requirements for AI-Empowered Clinical Decision Support System (AI-CDSS) design based on Knowledge Graph (KG) representation. The insights will be useful to the community of visualization researchers who work on ethical AI-CDSS design and conduct design studies with clinical partners.
LLM-Assisted Visual Analytics: Opportunities and Challenges
(The Eurographics Association, 2024) Hutchinson, Maeve; Jianu, Radu; Slingsby, Aidan; Madhyastha, Pranava; Hunter, David; Slingsby, Aidan
We explore the integration of large language models (LLMs) into visual analytics (VA) systems to transform their capabilities through intuitive natural language interactions. We survey current research directions in this emerging field, examining how LLMs are integrated into data management, language interaction, visualisation generation, and language generation processes. We highlight the new possibilities that LLMs bring to VA, especially how they can change VA processes beyond the usual use cases. We especially highlight building new visualisation-language models, allowing access of a breadth of domain knowledge, multimodal interaction, and opportunities with guidance. Finally, we carefully consider the prominent challenges of using current LLMs in VA tasks. Our discussions in this paper aim to guide future researchers working on LLM-assisted VA systems and help them navigate common obstacles when developing these systems.

Browse

Browsing Computer Graphics & Visual Computing (CGVC) 2024 by Issue Date

Results Per Page

Sort Options