Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Davide Scaramuzza

Davide Scaramuzza

Autonomous Quadrotor Flight despite Rotor Failure with Onboard Vision Sensors: Frames vs. Events


Feb 26, 2021
Sihao Sun, Giovanni Cioffi, Coen de Visser, Davide Scaramuzza

Figure 1 for Autonomous Quadrotor Flight despite Rotor Failure with Onboard Vision Sensors: Frames vs. Events
Figure 2 for Autonomous Quadrotor Flight despite Rotor Failure with Onboard Vision Sensors: Frames vs. Events
Figure 3 for Autonomous Quadrotor Flight despite Rotor Failure with Onboard Vision Sensors: Frames vs. Events
Figure 4 for Autonomous Quadrotor Flight despite Rotor Failure with Onboard Vision Sensors: Frames vs. Events
* IEEE Robotics and Automation Letters 6 (2), 580-587, 2021 
 * 8 pages, 10 figures 
  Access Paper or Ask Questions

Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction


Feb 18, 2021
Daniel Gehrig, Michelle Rüegg, Mathias Gehrig, Javier Hidalgo Carrio, Davide Scaramuzza

Figure 1 for Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
Figure 2 for Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
Figure 3 for Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
Figure 4 for Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
* IEEE Robotics and Automation Letters (RA-L), 2021 
  Access Paper or Ask Questions

Data-Driven MPC for Quadrotors


Feb 10, 2021
Guillem Torrente, Elia Kaufmann, Philipp Foehn, Davide Scaramuzza

Figure 1 for Data-Driven MPC for Quadrotors
Figure 2 for Data-Driven MPC for Quadrotors
Figure 3 for Data-Driven MPC for Quadrotors
Figure 4 for Data-Driven MPC for Quadrotors
* IEEE Robotics and Automation Letters (RA-L), 2021 
 * 8 pages 
  Access Paper or Ask Questions

Primal-Dual Mesh Convolutional Neural Networks


Oct 23, 2020
Francesco Milano, Antonio Loquercio, Antoni Rosinol, Davide Scaramuzza, Luca Carlone

Figure 1 for Primal-Dual Mesh Convolutional Neural Networks
Figure 2 for Primal-Dual Mesh Convolutional Neural Networks
Figure 3 for Primal-Dual Mesh Convolutional Neural Networks
Figure 4 for Primal-Dual Mesh Convolutional Neural Networks
* 34th Conference on Neural Information Processing Systems (NeurIPS 2020) 
 * Accepted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada. Code available at: https://github.com/MIT-SPARK/PD-MeshNet 
  Access Paper or Ask Questions

Learning Monocular Dense Depth from Events


Oct 22, 2020
Javier Hidalgo-Carrió, Daniel Gehrig, Davide Scaramuzza

Figure 1 for Learning Monocular Dense Depth from Events
Figure 2 for Learning Monocular Dense Depth from Events
Figure 3 for Learning Monocular Dense Depth from Events
Figure 4 for Learning Monocular Dense Depth from Events
* IEEE International Conference on 3D Vision (3DV), 2020 
  Access Paper or Ask Questions

Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation


Sep 30, 2020
Dimche Kostadinov, Davide Scaramuzza

Figure 1 for Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation
Figure 2 for Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation
Figure 3 for Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation
Figure 4 for Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation
* IAPR IEEE/Computer Society International Conference on Pattern Recognition (ICPR), Milan, 2021 
  Access Paper or Ask Questions

Flightmare: A Flexible Quadrotor Simulator


Sep 01, 2020
Yunlong Song, Selim Naji, Elia Kaufmann, Antonio Loquercio, Davide Scaramuzza

Figure 1 for Flightmare: A Flexible Quadrotor Simulator
Figure 2 for Flightmare: A Flexible Quadrotor Simulator
Figure 3 for Flightmare: A Flexible Quadrotor Simulator
Figure 4 for Flightmare: A Flexible Quadrotor Simulator

  Access Paper or Ask Questions

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning


Aug 18, 2020
Florian Fuchs, Yunlong Song, Elia Kaufmann, Davide Scaramuzza, Peter Duerr

Figure 1 for Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning
Figure 2 for Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning
Figure 3 for Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning
Figure 4 for Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning

  Access Paper or Ask Questions

Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning


Aug 07, 2020
Zichao Zhang, Davide Scaramuzza

Figure 1 for Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning
Figure 2 for Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning
Figure 3 for Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning
Figure 4 for Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning
* 18 pages, 15 figures 
  Access Paper or Ask Questions

Online Weight-adaptive Nonlinear Model Predictive Control


Aug 06, 2020
Dimche Kostadinov, Davide Scaramuzza

Figure 1 for Online Weight-adaptive Nonlinear Model Predictive Control
Figure 2 for Online Weight-adaptive Nonlinear Model Predictive Control
Figure 3 for Online Weight-adaptive Nonlinear Model Predictive Control
Figure 4 for Online Weight-adaptive Nonlinear Model Predictive Control
* IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, 2020 
  Access Paper or Ask Questions

CPC: Complementary Progress Constraints for Time-Optimal Quadrotor Trajectories


Aug 03, 2020
Philipp Foehn, Davide Scaramuzza

Figure 1 for CPC: Complementary Progress Constraints for Time-Optimal Quadrotor Trajectories
Figure 2 for CPC: Complementary Progress Constraints for Time-Optimal Quadrotor Trajectories
Figure 3 for CPC: Complementary Progress Constraints for Time-Optimal Quadrotor Trajectories
Figure 4 for CPC: Complementary Progress Constraints for Time-Optimal Quadrotor Trajectories

  Access Paper or Ask Questions

Learning High-Level Policies for Model Predictive Control


Jul 20, 2020
Yunlong Song, Davide Scaramuzza

Figure 1 for Learning High-Level Policies for Model Predictive Control
Figure 2 for Learning High-Level Policies for Model Predictive Control
Figure 3 for Learning High-Level Policies for Model Predictive Control
Figure 4 for Learning High-Level Policies for Model Predictive Control
* IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, 2020 
  Access Paper or Ask Questions

Deep Drone Acrobatics


Jun 11, 2020
Elia Kaufmann, Antonio Loquercio, René Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza

Figure 1 for Deep Drone Acrobatics
Figure 2 for Deep Drone Acrobatics
Figure 3 for Deep Drone Acrobatics
Figure 4 for Deep Drone Acrobatics
* Robotics, Science, and Systems (RSS), 2020 
 * 8 pages + 2 pages references. Video: https://youtu.be/2N_wKXQ6MXA. Code: https://github.com/uzh-rpg/deep_drone_acrobatics 
  Access Paper or Ask Questions

AlphaPilot: Autonomous Drone Racing


May 26, 2020
Philipp Foehn, Dario Brescianini, Elia Kaufmann, Titus Cieslewski, Mathias Gehrig, Manasi Muglikar, Davide Scaramuzza

Figure 1 for AlphaPilot: Autonomous Drone Racing
Figure 2 for AlphaPilot: Autonomous Drone Racing
Figure 3 for AlphaPilot: Autonomous Drone Racing
Figure 4 for AlphaPilot: Autonomous Drone Racing
* Accepted at Robotics: Science and Systems 2020, associated video at https://youtu.be/DGjwm5PZQT8 
  Access Paper or Ask Questions

Reference Pose Generation for Visual Localization via Learned Features and View Synthesis


May 13, 2020
Zichao Zhang, Torsten Sattler, Davide Scaramuzza

Figure 1 for Reference Pose Generation for Visual Localization via Learned Features and View Synthesis
Figure 2 for Reference Pose Generation for Visual Localization via Learned Features and View Synthesis
Figure 3 for Reference Pose Generation for Visual Localization via Learned Features and View Synthesis
Figure 4 for Reference Pose Generation for Visual Localization via Learned Features and View Synthesis
* 23 pages, 14 figures 
  Access Paper or Ask Questions

How to Train Your Event Camera Neural Network


Apr 09, 2020
Timo Stoffregen, Cedric Scheerlinck, Davide Scaramuzza, Tom Drummond, Nick Barnes, Lindsay Kleeman, Robert Mahony

Figure 1 for How to Train Your Event Camera Neural Network
Figure 2 for How to Train Your Event Camera Neural Network
Figure 3 for How to Train Your Event Camera Neural Network
Figure 4 for How to Train Your Event Camera Neural Network
* Edited to correct mistake in Table 4 (results for UnFlowNet were quoted in a couple of the MVSEC sequences from arXiv:1802.06898, rather than the EVFlowNet results) 
  Access Paper or Ask Questions

Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO


Mar 30, 2020
Balazs Nagy, Philipp Foehn, Davide Scaramuzza

Figure 1 for Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO
Figure 2 for Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO
Figure 3 for Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO
Figure 4 for Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO
* Submitted to IEEE International Conference on Intelligent Robots and Systems (IROS), 2020. Open-source implementation available at https://github.com/uzh-rpg/vilib 
  Access Paper or Ask Questions

Event-based Asynchronous Sparse Convolutional Networks


Mar 20, 2020
Nico Messikommer, Daniel Gehrig, Antonio Loquercio, Davide Scaramuzza

Figure 1 for Event-based Asynchronous Sparse Convolutional Networks
Figure 2 for Event-based Asynchronous Sparse Convolutional Networks
Figure 3 for Event-based Asynchronous Sparse Convolutional Networks
Figure 4 for Event-based Asynchronous Sparse Convolutional Networks

  Access Paper or Ask Questions

AirSim Drone Racing Lab


Mar 12, 2020
Ratnesh Madaan, Nicholas Gyde, Sai Vemprala, Matthew Brown, Keiko Nagami, Tim Taubner, Eric Cristofalo, Davide Scaramuzza, Mac Schwager, Ashish Kapoor

Figure 1 for AirSim Drone Racing Lab
Figure 2 for AirSim Drone Racing Lab
Figure 3 for AirSim Drone Racing Lab
Figure 4 for AirSim Drone Racing Lab
* 14 pages, 6 figures 
  Access Paper or Ask Questions

Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry


Mar 09, 2020
Giovanni Cioffi, Davide Scaramuzza

Figure 1 for Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry
Figure 2 for Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry
Figure 3 for Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry
Figure 4 for Tightly-coupled Fusion of Global Positional Measurements in Optimization-based Visual-Inertial Odometry

  Access Paper or Ask Questions

Geometry-aware Compensation Scheme for Morphing Drones


Mar 09, 2020
Amedeo Fabris, Kevin Kleber, Davide Falanga, Davide Scaramuzza

Figure 1 for Geometry-aware Compensation Scheme for Morphing Drones
Figure 2 for Geometry-aware Compensation Scheme for Morphing Drones
Figure 3 for Geometry-aware Compensation Scheme for Morphing Drones
Figure 4 for Geometry-aware Compensation Scheme for Morphing Drones
* Submitted to IEEE Conference on Intelligent Robots and Systems (IROS) 2020 
  Access Paper or Ask Questions

Event-Based Angular Velocity Regression with Spiking Networks


Mar 05, 2020
Mathias Gehrig, Sumit Bam Shrestha, Daniel Mouritzen, Davide Scaramuzza

Figure 1 for Event-Based Angular Velocity Regression with Spiking Networks
Figure 2 for Event-Based Angular Velocity Regression with Spiking Networks
Figure 3 for Event-Based Angular Velocity Regression with Spiking Networks
Figure 4 for Event-Based Angular Velocity Regression with Spiking Networks
* IEEE International Conference on Robotics and Automation (ICRA), Paris, 2020 
  Access Paper or Ask Questions

Voxel Map for Visual SLAM


Mar 04, 2020
Manasi Muglikar, Zichao Zhang, Davide Scaramuzza

Figure 1 for Voxel Map for Visual SLAM
Figure 2 for Voxel Map for Visual SLAM
Figure 3 for Voxel Map for Visual SLAM
Figure 4 for Voxel Map for Visual SLAM
* IEEE Conference on Robotics and Automation(ICRA), Paris, 2020 
  Access Paper or Ask Questions

Redesigning SLAM for Arbitrary Multi-Camera Systems


Mar 04, 2020
Juichung Kuo, Manasi Muglikar, Zichao Zhang, Davide Scaramuzza

Figure 1 for Redesigning SLAM for Arbitrary Multi-Camera Systems
Figure 2 for Redesigning SLAM for Arbitrary Multi-Camera Systems
Figure 3 for Redesigning SLAM for Arbitrary Multi-Camera Systems
Figure 4 for Redesigning SLAM for Arbitrary Multi-Camera Systems
* IEEE Conference on Robotics and Automation (ICRA), Paris, 2020 
  Access Paper or Ask Questions

Learning Depth via Interaction


Mar 02, 2020
Antonio Loquercio, Alexey Dosovitskiy, Davide Scaramuzza

Figure 1 for Learning Depth via Interaction
Figure 2 for Learning Depth via Interaction
Figure 3 for Learning Depth via Interaction
Figure 4 for Learning Depth via Interaction

  Access Paper or Ask Questions

Augmenting Visual Place Recognition with Structural Cues


Feb 29, 2020
Amadeus Oertel, Titus Cieslewski, Davide Scaramuzza

Figure 1 for Augmenting Visual Place Recognition with Structural Cues
Figure 2 for Augmenting Visual Place Recognition with Structural Cues
Figure 3 for Augmenting Visual Place Recognition with Structural Cues
Figure 4 for Augmenting Visual Place Recognition with Structural Cues

  Access Paper or Ask Questions

Registration made easy -- standalone orthopedic navigation with HoloLens


Jan 17, 2020
Florentin Liebmann, Simon Roner, Marco von Atzigen, Florian Wanivenhaus, Caroline Neuhaus, José Spirig, Davide Scaramuzza, Reto Sutter, Jess Snedeker, Mazda Farshad, Philipp Fürnstahl

Figure 1 for Registration made easy -- standalone orthopedic navigation with HoloLens
Figure 2 for Registration made easy -- standalone orthopedic navigation with HoloLens
Figure 3 for Registration made easy -- standalone orthopedic navigation with HoloLens
Figure 4 for Registration made easy -- standalone orthopedic navigation with HoloLens
* 6 pages, 5 figures, accepted at CVPR 2019 workshop on Computer Vision Applications for Mixed Reality Headsets (https://docs.microsoft.com/en-us/windows/mixed-reality/cvpr-2019) 
  Access Paper or Ask Questions