Topics

Here you find different topics for student research that can be custom tailored to research projects (INF-PM-FPA,INF-PM-FPG,CMS-PRO), Großer Beleg or student theses in a discussion with the supervisor. As a prerequisite students should have attended one or better several of our master level courses.

Theses, Große Belege and Research Projects

  • Brain Twisters (4D and more)
    • Space-time Slicing 4D of Time-Dependent Volume Data  (within ScaDS), video,  Marzan Tasnim Oyshi
    • 4D Soundini, Stefan Gumhold
      In a previous student thesis a simple ego-perspective hide&seek game in 4D space has been implemented where the player traces a virtual worm called fourdini that flees and hides in 4D space. The motivation behind the game is to provide a playful access to the understanding of 4D space. The implementation includes a navigation concept in 4D and a rendering approach based on 4D spheres that are used to represent fourdini as well as the game environment. The 4th dimension is rendered by overlaying several color shifted renderings of different 4D slices. In case fourdini is out of sight, a pointing concept is used to help the player find fourdini again. In this topic that pointing should be replaced by exploiting sound emited by fourdini's sibling soundini. Besides 3D sound an additional sound dimension should be used to provide information about relative 4D position of soundini with respect to the player. In a literature study on sound dimensions suitable choices shall be spotted and then compared with a prototypical implementation. Fourdini is implemented in C++ and OpenGL with the CGV framework that also supports 3D sound.
    • Efficient Out-of-Core Slicing of Multi-Dimensional Data, Stefan Gumhold
      Here we consider a scalar dataset organized in an nD-Array or n-Tensor, which is a vector for n=1, a matrix for n=2 and a volume for n=3. Besides space dimensions (x,y,z) further dimensions like time (t) and frequency (f) can be sampled providing multi-dimensional datasets with n>4. In practical applications these are very large and won't fit in main memory. This thesis should investigate an out-of-core strategy to support 1D, 2D and optionally 3D slicing of the data along any combination of axes. There core of this thesis is to come up with a data organization on disk that supports real-time streaming of 1D, 2D, 3D slices to support interactive exploration of the multi-dimensional dataset.
  • Immersive Technology

    • EnvirVis: Visualizing weather extremes in VR (within Scads.Ai), Marzan Tasnim Oyshi

      • Extension of FloodVis, check the video to know more

      • Visualize extreme weather outcomes like heavy rainfall, drought

    • Digital Twin of Bennewitz (within Scads.Ai), Marzan Tasnim Oyshi

      This topic is also an extension of FloodVis. In this project, we used LOD1 to represent Bennewitz - a municipality in Saxony. Your task would be to update the city in a realistic manner. Upon modeling the digital twin, you will need to incorporate the results with existing floodVis. 

    • Sandbox App Development Tianfang Lin

      In a previous student project a sandbox augmented with a kinect and a beamer was built and a software was developed that allows interactive exploration of terrain flooding where the sand is used as terrain input and the beamer to show a flooding simulation on top of the sand surface. The concept of using the sand surface as input device and the projection as feedback or output medium can serve as hardware platform for a large number of further interactive applications like simulation games, landscape / city / 3D modeling, sound design, and a lot more.
      After inspection of the sandbox students can design their own topics.

    • AR Looking Glass, Stefan Gumhold

      The successful histocaching app developed in a previous student lab provides a playful access to historic content in the current context by overlaying historic photographs in an augmented reality mode of a cellphone app. The original app provides historic content on the main campus of TU Dresden. In order to bridge distances to other Campus parts or other historic cites in Dresden or anywhere on the earth, this topic shall examine an augmented reality looking glass. Distant content should be made accessible based on the relative direction and distance to the user. The topic includes setting up example content, developing a distant content navigation as well as selection concept as well as an evaluation of how well the spatial context is understood by the user.

    • A VR-based method of 3D Object Reconstruction, video, Tianfang Lin

    • 3D Object Tracking for Cobotics in VR,  Tianfang Lin

    • Scene Graph Generation for Room-scale Point Clouds,  Tianfang Lin

    • Using an RGBD camera for real-time depth correction of stereo seethrough in VR

  • Rendering

    • Remote Interaction for Visualization and Labeling, Stefan Gumhold

      Video streaming has become an established feature in video gaming due to hardware support of video coding on most of recent GPUs. In this topic video streaming shall be examined for visualization applications such as volume rendering where high framerates can only be achieved on highend GPUs and for interactive labeling tools for which user studies can be made in home-office independent of the specific client machine. Preferably the implementation should build on the cgv framework implemented in C++ and OpenGL that already supports volume rendering and tracked object labeling of video data. The implementation can be specific to a single platform vendor for example using NVENC and NVDEC.

    • Holographic Rendering, Stefan Gumhold

      Holographic displays like the Looking Glass displays build on a high-resolution 4k or 8k display to show holograms at 60 fps. This allows holographic applications that allow real-time interaction with 3D content without any special glasses. To generate a single hologram, the to be displayed 3D scene is rendered from 45 different views. In this topic techniques shall be investigated that accelerate multiple OpenGL rendering of the same scene exploiting techniques like instanced rendering, geometry shaders or view morphing. Experience in OpenGL and C++ programming is expected.

    • Accelerating Virtual Human Rendering with Tensor Cores, Stefan Gumhold

      Extensive 3D scanning of static and moving people have let to parametric polygonal mesh models that can adapt shape and pose. To use these in real-time applications like video games or mixed reality collaboration several matrix-vector operations need to be evaluated on a per frame basis. Such operations can be accelerated on tensor cores of current GPUs. This topic shall implement a prototype for evaluation and rendering of parametric models purely on the GPU and evaluate the improvement in runtime performance and the change in energy usage.

  • Simulation and Physics

    • Contact Analysis on Ellipsoids, Stefan Gumhold

      Ellipsoids are a common abstraction for particles in simulation approaches. For large scale simulations contact analysis between ellipsoids becomes crutial. In a broad phase potential contact pairs are sorted out based on a spatial acceleration data structure that can be built fast such as a grid or a hashed grid. In the narrow phase each potential pair of particles is analyzed by determining the closest points on the ellipsoids or if the ellipsoids interpenetrate the points defining the deepest interpenetration. In this topic either the narrow or both phases should be studied and prototypically implemented based on a high potential approach selected on the foundation of a literature study. The approach should be evaluated by procesurally generated test data and the result of each implemented phase should be visualized in 3D.

  • Virtual Humans, Julien Fischer
    • Remote Avatars: Capturing, Transmission and Rendering of Human Avatars for Remote Collaboration
    • Automatic creation of (full-body) identikits using expressive parameterized human body models
      • NOTE: This topic is suited exclusively for the module "Analysis of a research topic". Upon successful completion and assessed feasibility, this topic may be used for a thesis
      • Identikits (or phantom images) are currently created either by an artist or with the help of computer programs and templates. Parameterized human body models like SMPL-X may offer another alternative to create identikits through modification of their generative parameters. The goal of this topic is to analyze whether this approach is realizable and if yes, how. More detailed information on this topic will be made available soon.
  • Scientific Visualization 

    • Guidance for Oblique Slicing, Stefan Gumhold

      Oblique slicing is an fast method for volume inspection and can be easily implemented in real-time. Still it is not used frequently in practice probably as it is not easy to adjust slices in an intuitive way. In this topic a guidance scheme shall be developed that makes slice adjustment for oblique slicing more intuitive. A possible approach is to analyse the sliced volume data in the vicinity of the current slice and to extract curve features that show how the data extends beyond the current slice. These curve features should be extracted on different scale levels showing very local to more global data behavior. Furthermore, slice adjustment shall be simplified by selection of a specific curve feature along which a 1D adjustment is possible.

    • Aggregated Views of 2D Trajectories, Stefan Gumhold

      Focus and context visualization is typically based on detailed and aggregated views. Large number of trajectories for example from traffic or tracked people are typically aggregated in histograms that show the denisty of moving objects that passed by a small region representing the histogram bin. Especially, in growded regions like high-traffic crossings or squares in pedestrian zones this simple aggregation approach does not show how fast and in which direction objects move. In this topic aggregation techniques shall be investigated that incorporate velocity and movement direction of objects in a potentially interactive aggregated view.

    • Visualization of 2D Trajectory with Orientation, Stefan Gumhold

      Trajectories over 2D domains frequently arise in traffic and logistic applications. Spatial mapping to line primitives ignores the orientation of moving objects. For vehicles the orientation mostly corresponds to the direction of motion. But for particles or objects in dynamic processes the orientation can change independent of the path. In this topic visual mappings shall be studied that show object orientation along 2D trajectories. Different mappings of orientation to visual attributes like color, texture orientation or height should be investigated and evaluated with respect to their effectiveness and expressiveness.

    • Visualization of 3D Trajectories with Orientation, Stefan Gumhold

      Trajectories over 3D domains frequently arise in air traffic and drone based logistic applications. Spatial mapping to line primitives ignores the orientation of moving objects. For planes and birds the orientation mostly corresponds to the direction of motion. But for drones or particles/objects in dynamic processes the orientation can change independent of the path. In this topic visual mappings shall be studied that show object orientation along 3D trajectories. Different mappings of orientation to visual attributes like color, texture orientation or height should be investigated and evaluated with respect to their effectiveness and expressiveness.

    • Visualization of 3D Trajectories of Agents that see, Stefan Gumhold

      Environment mapping, collision avoidance and navigation in unknown terrain demands for camera and/or 3D sensors on remote-controled or autonomous agents like cars, robots, or drones. In the analysis of the resulting evironment maps or in failure cases like crashes it is important to have access to the information what parts of the environment have been visible to the sensores of the agents for each time point. This motivates the visualization problem of trajectories with moving sensor frusti that shall be studied in this topic.

    • Space-time slicing in non-VR, Marzan Tasnim Oyshi
    • Interactive visualization of spiraling optical coherent tomography imagery, Stefan Gumhold
    • Plotting of real-time streaming data, Stefan Gumhold
      In traffic control centers a lot of real-time data of planes, cars or ships needs to be visualized. Furthermore, for autonomous cars the current law demands for a human overseer that can give guidance in critical situations. In this thesis plotting of data streams should be investigated with respect to the best possible incremental update strategy which potentially leads also to the lowest possible latency.
    • Visualization of multi-variate 2D scalar fields, Stefan Gumhold
      In medical dignostics often different imaging modalities are necessary for a proper diagnosis. In this thesis different scalar field visualization techniques like height-fields, mapping to color, extraction of iso-contours or using lighting parameters should be investigated. Evaluation should examine which combination of visualization techniques is efficient and which combination is to be avoided.
    • Volume Data and multi-GPU (in colaboration with Ivo Sbalzarini), Aryaman Gupta

      • Efficient volume raycasting on particle data, video

      • NVidia NVSHMEM for accelerating multi-GPU rendering, video

      • Optimizing multi-GPU VDI generation, video

  •  Computer vision and Machine Learning topics

    • AI in Current Tomography, Nishant Kumar                                                                    In Current Tomography, the electrical conductivity changes of the electrolyte influence the current flow inside electrolysis cells, due to which the induced magnetic field around the cell also shows those changes. As electrolysis products, gas bubbles are desired, but they impede further reactions, decrease the cell efficiency and are electrically not conductive. With the help of magnetic sensor technology and Biot-Savarts Law, it is possible to measure the bubble-induced magnetic-field fluctuations. However, to estimate the bubble positions, it is required to utilize the induced magnetic field and estimate the current distribution in the cell. The challenge is that the inverse process, i.e. determining high dimensional current distribution from a set of very few induced magnetic field measurements, is ill-posed. Therefore, this project shall explore advanced machine-learning techniques to solve this inverse problem. The data will be provided before the start of the project.

    • User Guided Image Restauration with Invertible Neural Networks, Stefan Gumhold
      Invertible Neural Networks (INN) can map data distributions invertably to a uniform Gaussian distribution in a latent space of the same dimension as the input space. In this work INNs shall be used for image restauration by generating for a given corrupted input image a trajectory in latent space based on gradient ascent of the Gaussian probability distribution. Mapping the trajectory back to image space yields an image morph from the destorted image into the image manifold of the distribution learned by the INN. A user interface shall be provided to allow for interactive exploration of this image morph that can be used for user guided image restauration.

    • Likelihood-based Outlier Detection for Image Classification, Nishant Kumar          The deployment of reliable AI models is crucial for autonomous driving and medical imaging applications. In our recent work, we developed a likelihood-based approach for detecting outlier box features in an object detection setup. This project aims to extend the work to an image classification problem on standard image benchmarks. The training scheme related to our outlier-aware object detection approach will be discussed before the start of the project. 

    • Multimodal Medical Image Fusion for clinical prognosis, Nishant Kumar                  Multimodal Brain imaging, such as DWI and T2-Flair, are two common MRI modalities that provide crucial insights into tumor presence. For example, the high-intensity signal on DWI indicates that the tumor has solid components, i.e., enhancing tumor. In contrast, a high-intensity signal on T2-Flair indicates that the tumor contains more liquid components and is already necrotic. As the tumor grows, it becomes necrotic and liquefied due to insufficient blood supply. Clinicians perform pre-operative imaging to judge the extent of the tumor in the brain before conducting the surgical intervention. Subsequently, they perform post-operative imaging to analyze any tumor residual and anticipate the likelihood of tumor recurrence. However, for clinicians, the visualization of contrasting tumor features in a single fused image for both pre and post-operative images should help better comprehend the possibility of tumor recurrence. Therefore, this project shall develop an efficient approach that provides meaningful fused images viable for clinical interpretation and post-operative decision-making. The volumetric MRI datasets and the tumor segmentation labels will be provided before the start of the project.                           

  • Particle tracking velocimetry in foams using radiography, Sascha Heitkam (pdf)

Topics already taken

  • Brain Twisters
    • Understanding 4D Space with a Hide&Seek Game, Stefan Gumhold
      Implement a 4D rendering pipeline with a 4D navigation approach as foundation for an interactive game where the player needs to catch the computer controlled figure that flees and tries to hide in 4D space
  • Immersive Technology
  • Virtual Humans
    • Avatar-Configurator: Assigning clothes and assets to a virtual human avatar slides
  • Scientific Visualization
    • Multi-channel Transfer Function Design for analyzing sliced microscopy data (within PoL), Stefan Gumhold
    • Immersive visualization of Morpheus' cellular automata simulation
      (see Morpheus project page),  Stefan Gumhold
    • Texture space grids with ticks and labels, Stefan Gumhold
      When visualizing quantitative data in plots or on surfaces, a grid with tickmarks and labels showing concrete values is essential for a quantitative analysis. Typically, a lot of line and text geometry is created and sent to the GPU. In this thesis a procedural texture approach should be studied where only basic information on grid extent, tickmark and label placement should be transfered along for example a rectangular geometry and all the geometry should be generated procedurally in the fragment shader based on texture coordinates. Optionally, an smooth change in tickmark and labels density can be procedurally implemented to adapt to the zoom level if the grids are embedded in 3D space
    • Interactive Visualization of Extreme Subset Sets, Stefan Gumhold
      The automatic control of agents such as delivery drones or autonomous cars can be done with action policies that propose in each state the next action such as "turn left!", "break!", "accelerate!", ... . Action policies can be implemented with planing approaches or reinforcement learning. Here we consider action policies for a multi-goal objective such as delivery with drones to a multiple recipents within the negotiated delivery time. To analize multi-goal policies, one can extract all goal subsets of minimal size that cannot be fulfilled together. Alternatively, one can extract goal subsets of maximal size that can be fulfilled together. The goal of this student research topic is to develop an interactive tool for the inspection of extrem (minimal or maximal) goal subsets that scales to large goal sets. A good starting point for literature research with lots of pictures with potential subset visualization techniques can be found here.
  •  Computer vision topics

    • Real-time masking of water surfaces in video stream, Sebastian Vogt

    • Deep Family Fake: Synthetic generation of family pictures from images of a person using deep neural networks, Nishant Kumar 

    • MetaFuse: Meta-parameter optimization for balanced medical image fusion video  Nishant Kumar

    • Art Project with Anton Ginzburg:  Sebastian Vogt
      • Crash Video Synthesis By Simulation And Domain Transfer video

  • Machine Learning Foundations, Dmitrij Schlesinger

    • Generative Feed Forward Networks pdf

About this page

Stefan Gumhold
Last modified: Jan 20, 2023
Page Actions