Cordelia Schmid, an Inria research director, has received the Humboldt Research Award for her work on computer vision spanning more than 20 years.
She was nominated for this scientific award by Michael Black, the director of the Perceiving Systems department at the Max Planck Institute for Intelligent Systems in Tübingen, Germany. As the director of the LEAR team and then the Thoth team since 1 January 2016, Cordelia Schmid is particularly interested in visual recognition linking invariant image descriptors with learning methods. Her research enables a computer to learn not only to interpret all types of real images and videos, but also to recognize objects, actions and places by learning large image and video bases containing more than 100 million images. Cordelia Schmid figures among the world’s precursors and leaders in the field of modern visual recognition methods; she is also named in the “Highly Cited Researchers 2015” list (source: Thomson Reuters).
Perception is essential for Intelligence
Einen Wagen mit Chauffeur könnte es irgendwann für jeden geben, wenn nämlich ein Roboter das Steuer übernimmt. Damit Autos auch ohne großen technischen Aufwand autonom fahren können, müssen Computer unübersichtliche Verkehrssituation jedoch mindestens genauso gut beurteilen wie der Mensch.
The 2015 PAMI Mark Everingham Prize was awarded to the Middlebury Dataset (Daniel Scharstein, Richard Szeliski, and team) for a series of datasets and on-line evaluations, starting with the Stereo datasets in 2001, and extending to Optical Flow, MRF and others, which have inspired many other datasets. Michael Black was part of the team behind the Optical Flow dataset and evaluation.
Ali Osman Ulusoy, Andreas Geiger and Michael Black receive the Best Paper Award at this years 3D Vision Conference for their paper "Towards Probabilistic Volumetric Reconstruction using Ray Potentials".
Andreas Geiger receiving the GCPR 2015 Best Paper Award from Reinhard Koch (president of DAGM) and Bastian Leibe (general chair of GCPR 2015) for their paper "Joint 3D Object and Layout Inference from a single RGB-D Image".
Researchers at the Max Planck Institute for Intelligent Systems unveil the world’s first high-resolution 4D body scanner and software to model detailed soft-tissue motion.
Everybody jiggles” according Dr. Michael Black, Director at the Max Planck Institute for Intelligent Systems (MPI-IS) in Tübingen, Germany. We may not like it, but how we jiggle says a lot about who we are. Our soft tissue (otherwise known as fat and muscle) deforms, wobbles, waves, and bounces as we move. These motions may provide clues about our risk for cardiovascular disease and diabetes. They also make us look real. Digital characters either lack natural soft-tissue motion or require time-consuming animation to make them believable. Now researchers at MPI-IS have captured people and how they jiggle in exacting detail and have created realistic 3D avatars that bring natural body motions to digital characters.
The Science2Start programme is geared towards scientists interested in founding start-ups and helps putting their business ideas in the field of life sciences into practice.
Detection of new or rapidly evolving melanocytic lesions is crucial for early diagnosis and treatment of melanoma.
Three new members elected to the Academy
Andreas Geiger has been awarded the KIT Doctoral Award
In his PhD thesis, Andreas Geiger has developed algorithms for 3D scene perception in autonomous vehicles which can help to improve traffic safety, reduce traffic jams and enable car rides for elderly or visually impaired people. His approach combines visual recognition using stereo cameras with probabilistic models which are able to determine the location and orientation of roads, lanes and other traffic participants.
Researchers at the Max Planck Institute for Intelligent Systems unveil new technology for motion and shape capture
The new technology (MoSh) will help animators jump the “Uncanny Valley” by turning a few moving dots into detailed body shapes that jiggle and deform like real humans. Researchers at the Max Planck Institute for Intelligent Systems in Tübingen, presented their Motion and Shape Capture (MoSh) study, which appeared in the journal ACM Transactions on Graphics, at SIGGRAPH Asia in Shenzhen on December 6, 2014. Devised by a team of researchers under the direction of Michael J. Black, Director of the Perceiving Systems department, MoSh is a method that allows animators to record the three-dimensional (3D) motion and shape of a real human and digitally “retarget” it to a new body shape. With MoSh, realistic virtual humans can populate games, the Internet, and virtual reality, while reducing animation costs for the special effects industry.