9 papers
Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics
Max Schwarz, Sven Behnke
Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics. We describe a synthesis pipelin…
Visual Descriptor Learning from Monocular Video
Umashankar Deekshith, Nishit Gajjar, Max Schwarz +1
Correspondence estimation is one of the most widely researched and yet only partially solved area of computer vision with many applications in tracking, mapping, recognition of obj…
ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation
Catherine Capellen, Max Schwarz, Sven Behnke
6D object pose estimation is a prerequisite for many applications. In recent years, monocular pose estimation has attracted much research interest because it does not need depth me…
Refining 6D Object Pose Predictions using Abstract Render-and-Compare
Arul Selvam Periyasamy, Max Schwarz, Sven Behnke
Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-lea…
Autonomous Bimanual Functional Regrasping of Novel Object Class Instances
Dmytro Pavlichenko, Diego Rodriguez, Christian Lenz +2
In human-made scenarios, robots need to be able to fully operate objects in their surroundings, i.e., objects are required to be functionally grasped rather than only picked. This…
Flexible Disaster Response of Tomorrow -- Final Presentation and Evaluation of the CENTAURO System
Tobias Klamt, Diego Rodriguez, Lorenzo Baccelliere +29
Mobile manipulation robots have high potential to support rescue forces in disaster-response missions. Despite the difficulties imposed by real-world scenarios, robots are promisin…