ATTENTION: This is a web archive! The IMS Group was split up in 2018 and does not exist anymore. Recent work of former members can be found at the VR/AR Group and the Computer Vision Group.

Interactive Media Systems, TU Wien

Image and Video Analysis & Synthesis

Contact: Margrit Gelautz

Our group performs basic and applied research on image and video analysis & synthesis with a focus on 3D scene reconstruction (especially, stereo analysis), video object segmentation, image matting and motion estimation. Current research activities concentrate on the application fields of assisted/autonomous driving and motion studies for human-robot interaction.

   Basic Information

The research group on Image and Video Analysis & Synthesis has a focus on computer vision and machine learning algorithms for assisted/autonomous driving, robotics and human motion studies, and 3D scene reconstruction. In collaboration with Microsoft Research Cambridge, our group has developed a web-based benchmark for alphamatting algorithms, which is hosted by TU Wien. Our current research activities in the field of robotics are tightly connected to the Doctoral College TrustRobots, which explores trustful human-robot interaction in a multi-disciplinary approach.

We maintain close collaboration with the company emotion3D GmbH, which was founded in 2011 as a spin-off of our research group. The company focuses on vision-based monitoring of automotive environments for safety and comfort applications.

We have been participants in two European COST Actions on High-dynamic Range Imaging and 3D Content Creation, Coding, and Transmission, which fostered networking activities among partners from over 30 European countries. In an ongoing research project ("CarVisionLight"), we collaborate with ZKW Group, a specialist in automotive lighting systems.

We are interested in both academic as well as industrial collaborations. Possible topics for collaboration include (but are not limited to)

  • computer vision and machine learning algorithms
  • stereo analysis
  • evaluation and generation of ground truth data
  • assisted/autonomous driving
  • robotics and human motion studies
  • high-dynamic range imaging

Our group recently moved to Computer Vision Lab. A new website will come up soon.

[JPEG] Teamphoto2020_klein.jpeg

                      [JPG] Gruppenfoto_IVAS_2018.jpg

                      (December 2018)

Featured Aspects of Our Work

CP
Research Project
Computational Perception
3D-TV
Research Project
Temporal-Consistent Stereo Matting for High-Quality Novel View Synthesis and Visual Effects
PAINT3D
Research Project
An industrial implementation of modern inpainting techniques for depth-based 3D film editing
Eva3D
Research Project
Evaluation of Methods for Generating Virtual Views for 3D Film Material
TrustRobots
Research Project
Doctoral College TrustRobots
CarVisionLight
Research Project
Combined 3D-Vision and Adaptive Front-Lighting System for Safe Autonomous Driving
Robust Depth 3D
Research Project
Robust Real-Time Depth Measurement Using Structured Light
Stereo Matching
Research Project
Evaluation and Design of Energy Functions for Global Stereo Matching
Changes
Research Project
Changes
Hyperion3D
Research Project
Intelligent Workflow Design for Low-Cost 3D Film Production
EvaWeb
Research Project
Evaluation of Methods for Live-Webcam-Videoconferencing
PersonalFilmAssistant
Research Project
Intelligent Assistant System for Video Production on Mobile Devices
ALPHAMAT
Research Project
Alpha Matting from Single and Multiple Images
3D VideoFusion
Research Project
High-quality 3D Video by Fusing Active and Passive Sensors
AVIS
Research Project
Advanced Vision-Based Sensing for Aerial Vehicles
HDRi
Research Project
HDRi: The digital capture, storage, transmission and display of real-world lighting

More information about our research is available on the projects and publications pages.