Topics | Nanovisualization

Reem Alzahrani

Ph.D. Student

Deep learning nlp Computer Vision Large Language Models vision language models Multi-Modal Large Language Models

Reem Alzahrani is an MS/PhD student at KAUST, working on Large Language Models and Vision-Language Models. Her research focuses on identifying and addressing the limitations of AI systems to improve their robustness and reliability.

Visualizing Trees

Prof. Xiaoru Yuan, Peking University

Apr 15, 12:00 - 13:00

B9 L2 H1 R2322

Peking University tree visualisation GoTree visual analytics map metaphor Social media

In this talk, I will introduce a few recent works on tree visualization. First I will present a visualization technique for comparing topological structures and node attribute values of multiple trees. I will further introduce GoTree, a declarative grammar supporting the creation of a wide range of tree visualizations. In the application side, visualization and visual analytics on social media will be introduced. The data from social media can be considered as graphs or trees with complex attributes. A few approaches using map metaphor for social media data visualization will be discussed.

Learning for Visual Data Synthesis and Analysis

Dr. Timo Ropinski, Professor, Visual Computing, Ulm University, Germany

Oct 7, 12:00 - 13:00

B9 L2 H1 R2322

Deep learning visual data synthesis visual data analysis estimation and segmentation Monte carlo methods

Abstract In this talk, I will present our recent advances in deep learning to synthesize and analyze visual data, such as images, volumes, and point clouds. The presented approaches are loosely aligned along the classical computer graphics rendering pipeline, whereby both structured and unstructured data are handled. I will first present concepts for learning in object space, i.e., directly on the data to be rendered. To realize different visual tasks, such as normal estimation and segmentation, I will discuss how Monte Carlo integration can be used to realize convolutions on point cloud data

Learning for Visual Data Synthesis and Analysis

Dr. Timo Ropinski, Professor, Visual Computing, Ulm University, Germany

Oct 7, 12:00 - 13:00

B9 L2 H1 R2322

Deep learning visual data synthesis visual data analysis estimation and segmentation Monte carlo methods

Abstract In this talk, I will present our recent advances in deep learning to synthesize and analyze visual data, such as images, volumes, and point clouds. The presented approaches are loosely aligned along the classical computer graphics rendering pipeline, whereby both structured and unstructured data are handled. I will first present concepts for learning in object space, i.e., directly on the data to be rendered. To realize different visual tasks, such as normal estimation and segmentation, I will discuss how Monte Carlo integration can be used to realize convolutions on point cloud data

Andres Villa

Postdoctoral Research Fellow

Continual Learning Multimodal learning Visual Language Models AI4Science Action understanding

Andres Villa is a Postdoctoral Fellow in the IVUL lab at King Abdullah University of Science and Technology (KAUST), focusing on AI for Science, Continual Learning, Visual Language Models, and Action Understanding.

Task-driven Automated Data Visualization

Dr. Yunhai Wang, Professor, Computer Science, Shandong University, China

Oct 2, 12:00 - 13:00

B9 L2 H2 R2325

data visualisation visualisation techniques parameters time series data high dimensional data EdWordle ShapeWordle

Abstract By providing visual representations of data, visualization can help people to carry out many data analysis tasks more effectively. Given a data set, however, there are often too many possible visualization techniques, with each technique having many parameters to be tuned. This arises the question is if it is possible to automatically design a visualization that is best suited to pursue a given task on given input data. With my group, I developed a number of techniques to achieve this goal for different data sets such as time-series data, high-dimensional data, text as well as graphs

Point cloud and volume data reconstruction and visualization

Dr. Ciril Bohak, Postdoctoral Researcher, Faculty of Computer and Information Science, University of Ljubljana, Slovenia

Sep 25, 13:00 - 14:00

B1 L2

point cloud volume data reconstruction visualization real-time rendering web-based framework

Abstract Our ongoing research on the reconstruction of aerial point cloud data includes reconstructing the parts of the data that are not captured by the airplane mounted LiDAR system due to the shadowing effect and lack of reflections. We are developing methods for reconstructing (1) building walls, (2) reconstruction of bridges and underlying terrain; (3) reconstruction of water surfaces of lakes and rivers, and (4) reconstruction of terrain overhangs. In all the cases we are merging the point cloud data with cadaster data or digital terrain model data for filling the gaps in the point cloud

Mehdi Zakroum

Postdoctoral Research Fellow, Computer, Electrical and Mathematical Sciences and Engineering

Cyber Security Web Security Trustworthy AI

Nizar Ajeeb

Researcher (former), King Abdullah University of Science and Technology

Programming language MATLAB data analysis Web Technologies

Full Time Researcher Full at King Abdullah University of Science and Technology.

Point cloud and volume data reconstruction and visualization

Dr. Ciril Bohak, Postdoctoral Researcher, Faculty of Computer and Information Science, University of Ljubljana, Slovenia

Sep 25, 13:00 - 14:00

B1 L2

point cloud volume data reconstruction visualization real-time rendering web-based framework

Abstract Our ongoing research on the reconstruction of aerial point cloud data includes reconstructing the parts of the data that are not captured by the airplane mounted LiDAR system due to the shadowing effect and lack of reflections. We are developing methods for reconstructing (1) building walls, (2) reconstruction of bridges and underlying terrain; (3) reconstruction of water surfaces of lakes and rivers, and (4) reconstruction of terrain overhangs. In all the cases we are merging the point cloud data with cadaster data or digital terrain model data for filling the gaps in the point cloud

Web-based 3D Visualization

Ivan Viola, Professor, Computer Science

Apr 10, 12:00 - 13:00

B9 L2 H2 H2

nanovisualization computer graphics 3D graphics WebGPU WebAssmbly

In this seminar I will present how to create 3D computer graphics and visualization systems for the web, using WebAssmbly and WebGPU language specifications, which are new, bleeding-edge technologies. Previously, accelerated graphics on the web was based on JavaScript libraries, which is still very popular, but they do not offer detailed memory management and code optimization, necessary for systems requiring high memory load and high computational demands. WebAssembly and WebGPU can be compiled from the C++ or Rust code, which also allows the deployment of the same codebase either for web or for the desktop-based applications.

Web-based 3D Visualization

Ivan Viola, Professor, Computer Science

Apr 10, 12:00 - 13:00

B9 L2 H2 H2

nanovisualization computer graphics 3D graphics WebGPU WebAssmbly

In this seminar I will present how to create 3D computer graphics and visualization systems for the web, using WebAssmbly and WebGPU language specifications, which are new, bleeding-edge technologies. Previously, accelerated graphics on the web was based on JavaScript libraries, which is still very popular, but they do not offer detailed memory management and code optimization, necessary for systems requiring high memory load and high computational demands. WebAssembly and WebGPU can be compiled from the C++ or Rust code, which also allows the deployment of the same codebase either for web or for the desktop-based applications.