986 citations
- University of KaiserslauternDE26 papers
- Moscow Institute of Physics and TechnologyRU6 papers
- Rheinland-Pfälzische Technische Universität Kaiserslautern-LandauDE6 papers
- Universität UlmDE6 papers
- University of KasselDE6 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- Karlsruhe Institute of TechnologyDE4 papers
- RWTH Aachen UniversityDE4 papers
- Technische Universität DarmstadtDE4 papers
- University of StuttgartDE4 papers
- Daimler Truck (Germany)3 papers
- ETH ZurichCH3 papers
4 papers · 2 filters
Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling
Sebastian Ramos, Stefan Gehrig, Peter Pinggera +2
The detection of small road hazards, such as lost cargo, is a vital capability for self-driving cars. We tackle this challenging and rarely addressed problem with a vision system t…
DeMoN: Depth and Motion Network for Learning Monocular Stereo
Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig +4
In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstraine…
The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts, Mohamed Omran, Sebastian Ramos +6
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, esp…
Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
Jonas Uhrig, Marius Cordts, Uwe Franke +1
Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphi…