Congrats to my team for finishing 2nd at the #AlphaPilot Autonomous Drone Racing World Championship! We completed the course in 15 sec, 3 sec slower than the winner! Congrats to the winner MAVLab - TU Delft ! Lockheed Martin Drone Racing League Our drone below! #UZH_en #AIRR #drones

Check our new paper "Redesigning SLAM for Arbitrary Multi-Camera Systems": novel generic visual SLAM front-end for arbitrary multicamera systems. No need to tune the parameters across different camera setups! PDF: rpg.ifi.uzh.ch/docs/ICRA20_Ku… youtu.be/JGL4H93BiNw Manasi Muglikar

Check out our #ICRA2020 paper: "Voxel Map for Visual SLAM". We propose a voxel-map representation that is both scalable and geometry-aware while being as efficient keyframe SLAM techniques. PDF: rpg.ifi.uzh.ch/docs/ICRA20_Mu… Manasi Muglikar #UZH #voxel #map #SLAM

Check out our #RSS2020 paper "AlphaPilot: Autonomous Drone Racing" which raced to the second place at the 2019 AlphaPilot Challenge by #DRL and #LockheedMartin. Paper: rpg.ifi.uzh.ch/docs/RSS20_Foe… Video: youtu.be/DGjwm5PZQT8 University of Zurich UZH IfI Universität Zürich #droneracing #machinelearning

Our #RSS2020 paper "AlphaPilot Autonomous Drone Racing" won the Best Systems Paper Award! Congrats to my team P. Foehn, D. Brescianini, Elia Kaufmann, Mathias Gehrig, Titus Cieslewski, Manasi Muglikar Paper: rpg.ifi.uzh.ch/docs/RSS20_Foe… Video : youtu.be/k6vGEj1ZZWc University of Zurich UZH President

Today on the #NCCRWomen campaign, we introduce you to Manasi Muglikar, an engineer and PhD student working with event cameras and computer vision at the Davide Scaramuzza lab in University of Zurich. Check out her video on YouTube and Instagram! youtu.be/GmcVfjrtx-U

We are open-sourcing a toolbox to facilitate event camera calibration. Neural network-based image reconstruction enables compatibility with any existing calibration toolbox. Code: github.com/uzh-rpg/e2calib Paper: rpg.ifi.uzh.ch/docs/CVPRW21_M… Manasi Muglikar Daniel Gehrig Davide Scaramuzza

We are open-sourcing a toolbox to facilitate event camera calibration! Neural network-based image reconstruction enables compatibility with any existing calibration toolbox! Code: github.com/uzh-rpg/e2calib Paper: rpg.ifi.uzh.ch/docs/CVPRW21_M… Manasi Muglikar Mathias Gehrig Daniel Gehrig

We are open-sourcing our toolbox to facilitate event camera calibration. Neural network-based image reconstruction to enable compatibility with any existing calibration toolbox. Code: github.com/uzh-rpg/e2calib Paper: rpg.ifi.uzh.ch/docs/CVPRW21_M… Mathias Gehrig Daniel Gehrig Davide Scaramuzza

We are excited to announce our new, indoor, drone-testing arena! Equipped with 36 Vicon cameras and with 30x30x8m of flight space, we can deploy advanced perception, learning, control algorithms to push vision-based agile drones to speeds over 60 km/h and accelerations over 5g!

Check out our #3DV2021 paper on Event-based Structure Light! We combine an #eventcamera with a laser-point projector to allow accurate depth estimation in highly dynamic scenes! Paper, Code, Data: rpg.ifi.uzh.ch/esl.html Kudos to Manasi Muglikar Guillermo Gallego Prophesee

New work on dense optical flow from event cameras is out! w/ Mario Millhäusler Daniel Gehrig Davide Scaramuzza 3-times lower error, robust to low-light and HDR, new dataset DSEC-Flow. #3DV oral paper: tinyurl.com/mrknud3a Code & Data: tinyurl.com/E-RAFT Video: youtu.be/dN8fl7-XfNw

Check out our #3DV2021 paper on Event-guided Depth-Sensing, in collaboration with Sony! We use an #eventcamera to guide a depth sensor to scan areas of interest with higher spatial density! Paper: rpg.ifi.uzh.ch/docs/3DV21_Mug… Video: youtu.be/Rvv9IQLYjCQ Kudos to Manasi Muglikar

Excited to present our #3DV2021 paper on Event-guided Depth-Sensing, in collaboration with Sony! We use an #eventcamera to guide a depth sensor to scan areas of interest with higher spatial density!

Apply before Feb 21st! "Predicting geomagnetic conditions on the 🌎 from multi-spectral images of the 🌞". Research in Germany - Initiative of the BMFTR TU Berlin Helmholtz Einstein Center Digital Future GFZ

Check out our #CVPR2023 paper on Shape from Polarization with #eventcameras, where we use a rotating polarizer to generate events. We achieve 2x acquisition speed as commercial polarization sensors! Paper, Code, Video: github.com/uzh-rpg/ESfP Kudos Manasi Muglikar

Find out more about our work on high speed shape from polarization with event cameras at #cvpr2023

Thrilled to wrap up my visit with the talented team at the Camera Culture Group, lead by Ramesh Raskar . It's been great experience, collaborating on the next generation of computational imaging.

Continuous-time optical flow from events and frames! Code and dataset from our #PAMI paper now available arxiv.org/abs/2203.13674