Eurographics Digital Library
This is the DSpace 7 platform of the Eurographics Digital Library.
- The contents of the Eurographics Digital Library Archive are freely accessible. Only access to the full-text documents of the journal Computer Graphics Forum (joint property of Wiley and Eurographics) is restricted to Eurographics members, people from institutions who have an Institutional Membership at Eurographics, or users of the TIB Hannover. On the item pages you will find so-called purchase links to the TIB Hannover.
- As a Eurographics member, you can log in with your email address and password from https://services.eg.org. If you are part of an institutional member and you are on a computer with a Eurographics registered IP domain, you can proceed immediately.
- From 2022, all new releases published by Eurographics will be licensed under Creative Commons. Publishing with Eurographics is Plan-S compliant. Please visit Eurographics Licensing and Open Access Policy for more details.
Recent Submissions
Task-Aware 3D Geometric Synthesis
(University of Toronto, 2024) Sellán, Silvia
This thesis is about the different ways in which three-dimensional shapes come into digital existence inside a computer. Specifically, it argues that this geometric synthesis process should be tuned to the specific end for which an object is modeled or captured, and proposes building algorithms specific to said end. The majority of this thesis is dedicated to how 3D shapes are designed, and introduces changes to this modeling process to incorporate manufacturing constraints (e.g., that an object can physically be built out of a specific material or with a specific machine), precomputed simulation data (e.g., an object’s response to an impact) or specific user inputs (e.g., 3D drawing in Virtual or Augmented Reality). Importantly, these changes include rethinking the ways in which geometry is commonly represented, instead introducing formats that benefit specific applications, as well as efficient algorithms for converting between them. By contrast, the latter part of this thesis concerns itself with the task of capturing real-world 3D surfaces, a process that necessarily involves reconstructing continuous mathematical objects from imperfect, noisy and occluded discrete information. This thesis introduces a novel, stochastic lens from which to study this fundamentally underdetermined process, allowing for the introduction of task-specific priors as well as quantifying the uncertainty of common algorithmic predictions. This perspective is shown to provide critical insights in common 3D scanning paradigms. While geometric capture is the natural first step in which to introduce this statistical perspective, the thesis ends by enumerating other tasks further along the geometric processing pipeline that could benefit from it.
Data-centric Design and Training of Deep Neural Networks with Multiple Data Modalities for Vision-based Perception Systems
(University of the Basque Country, 2023-06-12) Aranjuelo, Nerea
The advances in computer vision and machine learning have revolutionized the ability to build systems that process and interpret digital data, enabling them to mimic human perception and paving the way for a wide range of applications. In recent years, both disciplines have made significant progress, fueled by advances in deep learning techniques. Deep learning is a discipline that uses deep neural networks (DNNs) to teach machines to recognize patterns and make predictions based on data. Deep learning-based perception systems are increasingly prevalent in diverse fields, where humans and machines collaborate to combine their strengths. These fields include automotive, industry, or medicine, where enhancing safety, supporting diagnosis, and automating repetitive tasks are some of the aimed goals.
However, data are one of the key factors behind the success of deep learning algorithms. Data dependency strongly limits the creation and success of a new DNN. The availability of quality data for solving a specific problem is essential but hard to obtain, even impracticable, in most developments. Data-centric artificial intelligence emphasizes the importance of using high-quality data that effectively conveys what a model must learn. Motivated by the challenges and necessity of data, this thesis formulates and validates five hypotheses on the acquisition and impact of data in DNN design and training.
Specifically, we investigate and propose different methodologies to obtain suitable data for training DNNs in problems with limited access to large-scale data sources. We explore two potential solutions for obtaining data, which rely on synthetic data generation. Firstly, we investigate the process of generating synthetic training data using 3D graphics-based models and the impact of different design choices on the accuracy of obtained DNNs. Beyond that, we propose a methodology to automate the data generation process and generate varied annotated data by replicating a 3D custom environment given an input configuration file. Secondly, we propose a generative adversarial network (GAN) that generates annotated images using both limited annotated data and unannotated in-the-wild data. Typically, limited annotated datasets have accurate annotations but lack realism and variability, which can be compensated for by the in-the-wild data. We analyze the suitability of the data generated with our GAN-based method for DNN training.
This thesis also presents a data-oriented DNN design, as data can present very different properties depending on their source. We differentiate sources based on the sensor modality used to obtain the data (e.g., camera, LiDAR) or the data generation domain (e.g., real, synthetic). On the one hand, we redesign an image-oriented object detection DNN architecture to process point clouds from the LiDAR sensor and optionally incorporate information from RGB images. On the other hand, we adapt a DNN to learn from both real and synthetic images while minimizing the domain gap of learned features from data.
We have validated our formulated hypotheses in various unresolved computer vision problems that are critical for numerous real-world vision-based systems. Our findings demonstrate that synthetic data generated using 3D models and environments are suitable for DNN training. However, we also highlight that the design choices during the generation process, such as lighting and camera distortion, significantly affect the accuracy of the resulting DNN. Additionally, we show that a simulation 3D environment can assist in designing better sensor setups for a target task.
Furthermore, we demonstrate that GANs offer an alternative means of generating training data by exploiting labeled and existing unlabeled data to generate new samples that are suitable for DNN training without a simulation environment.
Finally, we show that adapting DNN design and training to data modality and source can increase model accuracy. More specifically, we demonstrate that modifying a predefined architecture designed for images to accommodate the peculiarities of point clouds results in state-of-the-art performance in 3D object detection. The DNN can be designed to handle data from a single modality or leverage data from different sources. Furthermore, when training with real and synthetic data, considering their domain gap and designing a DNN architecture accordingly improves model accuracy.
The MoBa Pregnancy and Child Development Dashboard: A Design Study
(The Eurographics Association, 2024) Ziman, Roxanne; Budich, Beatrice; Vaudel, Marc; Garrison, Laura; Garrison, Laura; Jönsson, Daniel
Visual analytics dashboards enable exploration of complex medical and genetic data to uncover underlying patterns and possible relationships between conditions and outcomes. In this interdisciplinary design study, we present a characterization of the domain and expert tasks for the exploratory analysis for a rare maternal disease in the context of the longitudinal Norwegian Mother, Father, and Child (MoBa) Cohort Study. We furthermore present a novel prototype dashboard, developed through an iterative design process and using the Python-based Streamlit App [TTK18] and Vega-Altair [VGH*18] visualization library, to allow domain experts (e.g., bioinformaticians, clinicians, statisticians) to explore possible correlations between women's health during pregnancy and child development outcomes. In conclusion, we reflect on several challenges and research opportunities for not only furthering this approach, but in visualization more broadly for large, complex, and sensitive patient datasets to support clinical research.
Leaving the Lab Setting: What We Can Learn About the Perception of Narrative Medical Visualizations from YouTube Comments
(The Eurographics Association, 2024) Mittenentzwei, Sarah; Murad, Danish; Preim, Bernhard; Meuschke, Monique; Garrison, Laura; Jönsson, Daniel
The general public is highly interested in medical information, particularly educational media about diseases, healthy biological processes such as pregnancy, and surgical procedures. Efforts to develop educational materials using data-driven approaches like narrative visualization exist, but studies are often performed in lab settings. Since there are few public sources for visualizations of medical image data, YouTube videos, which often contain 3D medical visualizations, are an important reference. We aim to better understand the user base of these videos. Therefore, we curated a dataset of 76 videos featuring medical 3D visualizations. We analyzed 14,550 comments across all videos using manual review and machine learning techniques, including natural language processing for sentiment and emotion analysis of user comments. While few comments directly link visual attributes or design choices to user sentiment, insights into users' motivation and opinions of specific design choices have emerged.
Why, What, and How to Communicate Health Information Visually: Reflections on the Design Process of Narrative Medical Visualization
(The Eurographics Association, 2024) Mittenentzwei, Sarah; Preim, Bernhard; Meuschke, Monique; Garrison, Laura; Jönsson, Daniel
Narrative visualization is an effective technique to convey information to a lay audience in an engaging, memorable, and persuasive manner. In the medical domain, we experienced that narrative medical visualizations meet high interest from clinicians and epidemiologists as storytelling is a promising approach to conveying complex medical topics in the context of patient education and public health by utilizing medical data. These endeavors from the computer science domain are mirrored by the interdisciplinary research topic of health communication. With this work, we reflect on our past experiences by (1) showing where narrative medical visualization is applicable to solve problems clinicians face in their work, (2) summarizing all findings within a story design process, describing the key points in creating a story and how they relate to each other, and (3) highlighting parallels and insights from health communication research that can improve future narrative medical visualizations. In doing so, we aim to provide the research community with a toolkit to support the design of narrative medical visualizations.