MZ

FotoFirst NameLast NamePosition
Klaus Hildebrandt Applies Geometry
Matthias Hullin Computational Transient Imaging
Ivo Ihrke Generalized Image Acquisition and Analysis
Andreas Karrenbauer Discrete Optimization
Michael Kerber Topological and Geometric Computing
Haricharan Lakshman Immersive Video
Hendrik Lensch General Appearance Acquisition
Hendrik Lensch General Appearance Acquisition
Yangyan Li Semantic Reconstruction from Point Cloud
Markus Magnor Graphics - Optics - Vision

Researcher


Dr. Michael Zollhöfer


Visual Computing, Deep Learning and Optimization

Name of Research Group: Visual Computing, Deep Learning and Optimization
Homepage Research Group: web.stanford.edu/~zollhoef
Personal Homepage: zollhoefer.com
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.

Researcher

Name of Researcher
Carsten Stoll
Homepage of Research Group
First Name
Carsten
Last Name
Stoll
Foto
url_foto
wp.mpi-inf.mpg.de/mpc-vcc/files/2012/01/stoll.jpg
Phone
Position
Optical Performace Capture
Categories
Former Groups
Research Mission
Creating high-quality and realistic virtual content is nowadays an important task for modern virtual worldsMe games and movies. While it is possible to roughly capture the motion and static shape of performers and scenes, capturing subtle surface motion details and appearance of actors (such as muscle bulging, cloth motion or facial wrinkles) and details of real scenes (such as moving leaves on trees) is still a challenging problem. The group focuses on researching novel techniques for capturing and processing highly detailed models of performers and scenes in motion using optical methods. Recent years have seen remarkable advances in the field, and so called performance capture methods have been developed that are able to capture motion, coherent geometry and appearance from a sparse set of input videos. However, many algorithms to date still do not produce results on a quality level that would be necessary to apply them in production environments. Achieving high-quality reconstructions that satisfy the requirements of these environments with as little human interaction as possible provide a whole new set of research challenges. In our work we plan to develop new methods for simultaneous motion, geometry and appearance acquisition that bring us closer to the goal of reconstructing completely realistic virtual performances and scenes.
mission_rtf
Name of Research Group
Optical Performace Capture

Personal Info

Photo