FotoFirst NameLast NamePosition
Mykhaylo Andriluka People Detection and Tracking
Roland Angst Vision, Geometry, and Computational Perception
Tamay Aykut
Vahid Babaei
Pierpaolo Baccichet Distributed Media Systems
Volker Blanz Learning-Based Modeling of Objects
Volker Blanz Learning-Based Modeling of Objects
Martin Bokeloh Inverse Procedural Modeling
Adrian Butscher Geometry Processing and Discrete Differential Geometry
Renjie Chen Images and Geometry


Dr. Michael Zollhöfer

Visual Computing, Deep Learning and Optimization

Name of Research Group: Visual Computing, Deep Learning and Optimization
Homepage Research Group:
Personal Homepage:
Mentor Saarbrücken: Hans-Peter Seidel
Mentor Stanford: Pat Hanrahan
Research Mission: The primary focus of my research is to teach computers to reconstruct and analyze our world at frame rate based on visual input. The extracted knowledge is the foundation for a broad range of applications not only in visual effects, computer animation, autonomous driving and man-machine interaction, but is also essential in other related fields such as medicine and biomechanics. Especially, with the increasing popularity of virtual, augmented and mixed reality, there comes a rising demand for real-time low latency solutions to the underlying core problems.    My research tackles these challenges based on novel mathematical models and algorithms that enable computers to first reconstruct and subsequently analyze our world. The main focus is on fast and robust algorithms that approach the underlying reconstruction and machine learning problems for static as well as dynamic scenes. To this end, I develop key technology to invert the image formation models of computer graphics based on data-parallel optimization and state-of-the-art deep learning techniques.    The extraction of 3D and 4D information from visual data is highly challenging and under-constraint, since image formation convolves multiple physical dimensions into flat color measurements. 3D and 4D reconstruction at real-time rates poses additional challenges, since it involves the solution of unique challenges at the intersection of multiple important research fields, namely computer graphics, computer vision, machine learning, optimization, and high-performance computing. However, a solution to these problems provides strong cues for the extraction of higher-order semantic knowledge. It is incredibly important to solve the underlying core problems, since this will have high impact in multiple important research fields and provide key technological insights that have the potential to transform the visual computing industry. In summer 2019 Michael Zollhöfer joined Facebook.


Name of Researcher
Ivo Ihrke
Homepage of Research Group
First Name
Last Name
Generalized Image Acquisition and Analysis
Former Groups
Research Mission
Our group is interested in devising novel imaging devices and reconstruction techniques mainly for 3D acquisition, especially in the case of difficult to scan objects and surfaces. We want to extend the capabilities of current 3D scanning devices by analyzing the image formation process in general cameras and using the devised knowledge for the design of improved devices. In doing so we aim at capturing more information than is possible with todays cameras. The tool to achieve this goal is an analysis of what we call plenoptic imaging. The so called plenoptic function is a useful concept to describe the visual world around us. It states that "everything that can be seen'' (and possibly much more) can be described by a 7-dimensional function that describes the intensity of light at every position in space (3 dimensions) in every viewing direction (2 dimensions) for every wavelength of light (1 dimension) and at every point in time (1 dimension). Current cameras only record a two-dimensional image out of the 7 possible dimensions. Our group aims at analyzing novel designs that can capture more of the vast information hidden in the light surrounding us. Simultaneously, we perform research on how this additional information can be used to help the computer infer more knowledge about the three-dimensional world we live in. The acquired data can be used for a multitude of purposes such as computational photo-realistic view synthesis of real world objects, computerized modification and re-assembly of their digital counterparts, sharing and collaboration using digital object descriptions but also scientific analysis of and model development for hitherto unexplored visual effects.
Name of Research Group
Generalized Image Acquisition and Analysis

Personal Info