Profile cover photo
Profile photo
Andrew Davison
2,252 followers -
Robot Vision, Imperial College London
Robot Vision, Imperial College London

2,252 followers
About
Posts

Post has shared content
Nice to see Parrot back with a new consumer drone.
Add a comment...

Post has shared content
New Google blog on robot Learning.
Designing robots that can observe their surroundings and decide the best course of action, while reacting to unexpected outcomes, is exceptionally difficult. Visit our blog to see what researchers from Google and X are doing to tackle this challenge.
Add a comment...

Post has shared content
I collaborated with +Taihú Pire, +Rodrigo Baravalle and +Ariel D'Alessandro on real-time depth stereo fusion for S-PTAM. Check the results on the video! We made the code available:

https://github.com/CIFASIS/dense-sptam

The details are on the following paper, accepted in the ROBOTICA journal

Taihú Pire, Rodrigo Baravalle, Ariel D'Alessandro and Javier Civera, Real-time dense map fusion for stereo SLAM, Robótica, 2018
Draft here: http://webdiis.unizar.es/~jcivera/papers/pire_etal_robotica18.pdf

Video showing results on other KITTI sequences:

https://youtu.be/yPAoFu_LhhA
Add a comment...

Post has attachment
At the anti Brexit march in London today.
Photo
Add a comment...

Post has attachment
We got a Best Paper Honourable Mention for CodeSLAM at CVPR. Congrats to +Michael Blösch , +Jan Czarnowski , +Ronnie Clark and +Stefan Leutenegger from the Dyson Robotics Lab.
Add a comment...

Post has attachment
CVPR daily, always nice to read!
Add a comment...

Post has attachment
SIGGRAPH paper and video now online for +Thomas Whelan's new work on reflective surface reconstruction with Michael Goesele which is the first proper look at the SLAM/reconstruction technology from Facebook Reality Labs (formerly the Surreal Group at Oculus).

Paper and video here:
https://www.gcc.tu-darmstadt.de/home/proj/mirror_reconstruction/mirror_reconstruction.en.jsp
Photo
Add a comment...

Post has attachment
Great talks and big audience at the Workshop on Deep Learning for Visual SLAM at CVPR.
Photo
Add a comment...

Post has attachment
If you are at CVPR next week, please join us on Monday for the Workshop in Deep Learning for Visual SLAM, organised by +Ronnie Clark, +Sudeep Pillai, +Alex Kendall, +Will Maddern, +Stefan Leutenegger and myself. We've got a great set of invited speakers as well as submitted talks and posters. The full schedule is available here:
http://visualslam.ai/schedule.html

and the full text for the submitted papers is already online here:
http://openaccess.thecvf.com/CVPR2018_workshops/CVPR2018_W9.py
Photo
Add a comment...

Post has shared content
Add a comment...
Wait while more posts are being loaded