Andreas GTC Europe talk on Deep Models for 3D Reconstruction is now available.
The German Pattern Recognition Award is awarded once a year to one young researcher in computer vision, pattern recognition or machine learning at an age of 35 years or less and sponsored by the Daimler AG with 5000€.
3D reconstruction from multiple 2D images is an inherently ill-posed problem. Prior knowledge is required to resolve ambiguities and probabilistic models are desirable to capture the ambiguities in the reconstructed model. In this talk, I will present two recent results tackling these two aspects. First, I will introduce a probabilistic framework for volumetric 3D reconstruction where the reconstruction problem is cast as inference in a Markov random field using ray potentials. Our main contribution is a discrete-continuous inference algorithm which computes marginal distributions of each voxel's occupancy and appearance. I will show that the proposed algorithm allows for Bayes optimal predictions with respect to a natural reconstruction loss. I will further demonstrate several extensions which integrate non-local CAD priors into the reconstruction process. In the second part of my talk, I will present a novel framework for deep learning with 3D data called OctNet which enables 3D CNNs on high-dimensional inputs. I will demonstrate the utility of the OctNet representation on several 3D tasks including classification, orientation estimation and point cloud labeling. Finally, I will present an extension of OctNet called OctNetFusion which jointly predicts the space partitioning function with the output representation, resulting in an end-to-end trainable model for volumetric depth map fusion.
NVIDIA CEO Jensen Huang presented the NVAIL AI Labs with the very first Tesla V100 GPUs, based on NVIDIA's Volta architecture. MPI-IS is among the top centers working at the leading edge of deep learning in computer vision. As such it is recognized by NVIDIA as one of its NVAIL labs and giving the MPI access to the best and latest NVIDIA technology. Huang unveiled these new GPUs at CVPR saying that he wants to put them in the hands of researchers first.
The Heinz Maier-Leibnitz Prize is recognized as the most important science award in Germany to early career researchers. It was awarded May 3rd, 2017 in Berlin.
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.
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".
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.