Opportunities

SmartVidente is a research project for Augmented Reality visualization of underground infrastructure such as water, heat pipes, power lines and communication cables.

3D Features for Action Recognition

Create a system to interact with your computer through novel 3D sensing

Master Project

Develop a Graphical User Interface (GUI) as frontend to our 3D Reconstruction pipeline that allows configuration through easy access to parameters and direct feedback through visualization of intermediate results.

Automatische Anpassung der Stereo-Kalibrierung eines Überwachungssystems

The Ludwig Boltzmann Institute for Clinical Forensic Imaging (LBI-CFI) has an interest in estimating the age of a subject from medical imaging (MR) data. This involves detection, segmentation and classification of age-relevant structures from 3D volumes.

Development of visualization and interaction techniques for mobile augmented reality using an eye-based tracker.

Augmented Reality on the IPhone

Augmented Virtuality Game Or Demo

Extending Augmented Reality with Multiple Perspectives

Cloud-based Localization on Smartphones

Topics tailored to student's abilities

Extend an existing bundle adjustment problem solver to allow for GPS camera positions and ground control points (GCPs) to be integrated into the optimization of 3D positions of cameras and reconstructed scene points.

The goal of this project is an inspection tool for damaged cables in a client-server system.

Detection and analysis of human behavior in natural environments

Build a user interface for interactive Super-Resolution

Implementation and evaluation of State-of-the-Art line-segment detectors for 3D reconstruction.

Develop a GUI-based tool for the alignment of aerial images to Google Maps or OpenStreetMap for georeferencing aerial triangulation data.

Explore new interaction methods of replaying geo-referenced videos.

Research and implementation of state-of-the-art inpainting methods.

Tracking and estimating hand gesture and pose in 3D depth images

Extend an existing Structured-Light sensor with diverse depth cameras

Evaluate the feasability of large scale image search approaches on mobile phones.

Goal of the project is to implement a proof of concept for a plugin free HTML5 based Augmented Reality system.

Image Morphing for Mixed Reality

Develop new interaction techniques with physical objects for augmented reality.

Extend and improve various parts of the existing Realtime 3D-Reonstruction pipeline

Electrical insulators should be detected in highly cluttered aerial images for visual inspection

View Planning for Micro Aerial Vehicels for accurate 3D reconstruction

Construct an efficient GPU-based implementation for measuring visual saliency and visual clutter.

The goal of this project is to design, implement and apply a library for remotely logging the user interactions and sensor status for Augmented Reality applications on Android smartphones.

A smartphone based software should be developed, which is capable of detecting and segmenting melanomas from the camera image.

Messdatenvisualisierung mit Augmented Reality

A Mobile Observation System for Handheld AR based on Cameras and Microphones should be implemented

Fast and robust localization of text on mobile devices.

Design und Entwicklung eines modularen GUI-Toolkits für Mobile Phones

Adapt an existing camera-space multi-image matching algorithm to allow matching of images in object space.

Develop a tool for texturing 3D meshes of objects by blending texture images from multiple views.

Integrate additional viewpoints (e.g. mirrors) into the current view to investigate the world without moving

Extensions of the FlowLib and the corresponding user interface.

Work on simulation mesh refinement and unstructured grid visualization

Transforming point clouds produced by reconstruction algorithms to a consistent mesh

Aufnahme von HDR Bildern in Echtzeit auf Smartphones mit speziellen Kameraeigenschaften

For the Virtual Dressing Room project, photo realistic visualization of garments is vital. Physical simulation of mesh positions is already implemented (see next figure), but material shading needs to be improved. To achieve this goal the general concept

Design aids/cues to understand the presentation of multiple perspectives within Augmented Reality (AR).

Implement an algorithm that is able to robustly extract a triangle mesh from a point cloud obtained from multiple depth maps that may contain outliers.

Optimize the ICG submission system

Build a Taskmanager for the GPU using Softshell

Advance our special Volume Renderer with an interesting feature