Search Results

Now showing 1 - 6 of 6
  • Item
    A Generative Adversarial Network for Upsampling of Direct Volume Rendering Images
    (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Jin, Ge; Jung, Younhyun; Fulham, Michael; Feng, Dagan; Kim, Jinman
    Direct volume rendering (DVR) is an important tool for scientific and medical imaging visualization. Modern GPU acceleration has made DVR more accessible; however, the production of high‐quality rendered images with high frame rates is computationally expensive. We propose a deep learning method with a reduced computational demand. We leveraged a conditional generative adversarial network (cGAN) to upsample DVR images (a rendered scene), with a reduced sampling rate to obtain similar visual quality to that of a fully sampled method. Our dvrGAN is combined with a colour‐based loss function that is optimized for DVR images where different structures such as skin, bone, . are distinguished by assigning them distinct colours. The loss function highlights the structural differences between images, by examining pixel‐level colour, and thus helps identify, for instance, small bones in the limbs that may not be evident with reduced sampling rates. We evaluated our method in DVR of human computed tomography (CT) and CT angiography (CTA) volumes. Our method retained image quality and reduced computation time when compared to fully sampled methods and outperformed existing state‐of‐the‐art upsampling methods.
  • Item
    BI‐LAVA: Biocuration With Hierarchical Image Labelling Through Active Learning and Visual Analytics
    (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Trelles, Juan; Wentzel, Andrew; Berrios, William; Shatkay, Hagit; Marai, G. Elisabeta
    In the biomedical domain, taxonomies organize the acquisition modalities of scientific images in hierarchical structures. Such taxonomies leverage large sets of correct image labels and provide essential information about the importance of a scientific publication, which could then be used in biocuration tasks. However, the hierarchical nature of the labels, the overhead of processing images, the absence or incompleteness of labelled data and the expertise required to label this type of data impede the creation of useful datasets for biocuration. From a multi‐year collaboration with biocurators and text‐mining researchers, we derive an iterative visual analytics and active learning (AL) strategy to address these challenges. We implement this strategy in a system called BI‐LAVA—Biocuration with Hierarchical Image Labelling through Active Learning and Visual Analytics. BI‐LAVA leverages a small set of image labels, a hierarchical set of image classifiers and AL to help model builders deal with incomplete ground‐truth labels, target a hierarchical taxonomy of image modalities and classify a large pool of unlabelled images. BI‐LAVA's front end uses custom encodings to represent data distributions, taxonomies, image projections and neighbourhoods of image thumbnails, which help model builders explore an unfamiliar image dataset and taxonomy and correct and generate labels. An evaluation with machine learning practitioners shows that our mixed human–machine approach successfully supports domain experts in understanding the characteristics of classes within the taxonomy, as well as validating and improving data quality in labelled and unlabelled collections.
  • Item
    HPSCAN: Human Perception‐Based Scattered Data Clustering
    (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Hartwig, S.; Onzenoodt, C. v.; Engel, D.; Hermosilla, P.; Ropinski, T.
    Cluster separation is a task typically tackled by widely used clustering techniques, such as k‐means or DBSCAN. However, these algorithms are based on non‐perceptual metrics, and our experiments demonstrate that their output does not reflect human cluster perception. To bridge the gap between human cluster perception and machine‐computed clusters, we propose HPSCAN, a learning strategy that operates directly on scattered data. To learn perceptual cluster separation on such data, we crowdsourced the labeling of bivariate (scatterplot) datasets to 384 human participants. We train our HPSCAN model on these human‐annotated data. Instead of rendering these data as scatterplot images, we used their and point coordinates as input to a modified PointNet++ architecture, enabling direct inference on point clouds. In this work, we provide details on how we collected our dataset, report statistics of the resulting annotations, and investigate the perceptual agreement of cluster separation for real‐world data. We also report the training and evaluation protocol for HPSCAN and introduce a novel metric, that measures the accuracy between a clustering technique and a group of human annotators. We explore predicting point‐wise human agreement to detect ambiguities. Finally, we compare our approach to 10 established clustering techniques and demonstrate that HPSCAN is capable of generalizing to unseen and out‐of‐scope data.
  • Item
    Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions
    (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Hoque, E.; Islam, M. Saidul
    Natural language and visualization are two complementary modalities of human communication that play a crucial role in conveying information effectively. While visualizations help people discover trends, patterns and anomalies in data, natural language descriptions help explain these insights. Thus, combining text with visualizations is a prevalent technique for effectively delivering the core message of the data. Given the rise of natural language generation (NLG), there is a growing interest in automatically creating natural language descriptions for visualizations, which can be used as chart captions, answering questions about charts or telling data‐driven stories. In this survey, we systematically review the state of the art on NLG for visualizations and introduce a taxonomy of the problem. The NLG tasks fall within the domain of natural language interfaces (NLIs) for visualization, an area that has garnered significant attention from both the research community and industry. To narrow down the scope of the survey, we primarily concentrate on the research works that focus on text generation for visualizations. To characterize the NLG problem and the design space of proposed solutions, we pose five Wh‐questions, why and how NLG tasks are performed for visualizations, what the task inputs and outputs are, as well as where and when the generated texts are integrated with visualizations. We categorize the solutions used in the surveyed papers based on these ‘five Wh‐questions’. Finally, we discuss the key challenges and potential avenues for future research in this domain.
  • Item
    The State of the Art in User‐Adaptive Visualizations
    (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Yanez, Fernando; Conati, Cristina; Ottley, Alvitta; Nobre, Carolina
    Research shows that user traits can modulate the use of visualization systems and have a measurable influence on users' accuracy, speed, and attention when performing visual analysis. This highlights the importance of user‐adaptive visualization that can modify themselves to the characteristics and preferences of the user. However, there are very few such visualization systems, as creating them requires broad knowledge from various sub‐domains of the visualization community. A user‐adaptive system must consider which user traits they adapt to, their adaptation logic and the types of interventions they support. In this STAR, we survey a broad space of existing literature and consolidate them to structure the process of creating user‐adaptive visualizations into five components: Capture Ⓐ from the user and any relevant peripheral information. Perform computational Ⓑ with this input to construct a Ⓒ . Employ Ⓓ logic to identify when and how to introduce Ⓔ . Our novel taxonomy provides a road map for work in this area, describing the rich space of current approaches and highlighting open areas for future work.
  • Item
    A Particle‐Based Approach to Extract Dynamic 3D FTLE Ridge Geometry
    (Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) Stelter, Daniel; Wilde, Thomas; Rössl, Christian; Theisel, Holger
    Lagrangian coherent structures (LCS) is an important concept for the visualization of unsteady flows. They describe the boundaries of regions for which material transport stays mostly coherent over time which can help for a better understanding of dynamical systems. One of the most common techniques for their computation is the extraction of ridges from the finite‐time Lyapunov exponent (FTLE) field. FTLE ridges are challenging to extract, both in terms of accuracy and performance, because they expose strong gradients of the underlying field, tend to come close to each other and are dynamic with respect to different time parameters. We present a new method for extracting FTLE ridges for series of integration times which is able to show how coherent regions and their borders evolve over time. Our techniques mainly build on a particle system which is used for sampling the ridges uniformly. This system is highly optimized for the challenges of FTLE ridge extraction. Further, it is able to take advantage of the continuous evolvement of the ridges which makes their sampling for multiple integration times much faster. We test our method on multiple 3D datasets and compare it to the standard Marching Ridges technique. For the extraction examples our method is 13 to over 300 times faster, suggesting a significant advantage.