It's heartbreaking to see a hit-piece written about my friend Andrew Huberman (Andrew D. Huberman, Ph.D.). I know him very well, and can definitively say that he is a great human being, scientist, and educator. Hit-piece attacks like this are simply trash click-bait journalism desperately

Computer Vision conference's acceptance criteria these days: #CVPR2024 #eccc2024 #AI #ComputerVision

Good luck monocular depth estimation that estimates ‘metric’ scale :)

We have released the code of Wild Visual Navigation (WVN). This is a joint effort with Jonas Frey, Piotr Libera, Nived Chebrolu, Georg Martius, Cesar Cadena, Marco Hutter, Maurice Fallon at Robotic Systems Lab Oxford Dynamic Robot Systems Intelligent Systems A short thread 🧵 x.com/dynamicrobots/…

I'm #hiring! 🤩 I'm looking for a fantastic new #PhD candidate to join my research group at MAVLab - TU Delft and shape the future of #robotic #learning and path #planning. Apply before 12 June! TU Delft Link: tudelft.nl/over-tu-delft/…

I will be presenting at #ICRA2024 our work on large-scale lidar-visual NeRF! Please stop by and have a chat! 16:30 - 18:00 | Thu 16 May | NT - G403 | ThCT25.05.

I’m presenting LEXIS on Thursday at #ICRA2024! Oral Session: SLAM V | 13:30 - 15:00 | Thurs 16 May | NT-G404 | ThBT26.09 Poster Presentation: 16:30-18:00 | Thurs 16 May | Exhibition Hall | ThCT26.09 Project page: ori-drs.github.io/projects/lexis My new website: ckassab.github.io

Today we had the honor of hosting Andrew Davison in the Oxford Robotics Institute seminar. He gave a great overview of the SLAM research he has led since he was a student at Oxford (some happened at the very same building we had the talk!), and also really exciting new projects from his lab.

Jon Barron Now we're coming for AI's jobs!

🎉 Exciting news! We've earned Blue Ribbon TC status from IEEE RAS, recognizing our work in organizing workshops & mentoring events. Now’s the perfect time to get involved—join us for mentoring & social events, get workshop sponsorships, and more! 💡🚀 👉ieee-ras-crv.github.io

Check out my colleague Rowan Border’s cool work on aerial 3d mapping!

If you are at #CoRL2024 Conference on Robot Learning and work on locomotion or bioinspiration, please come to our workshop "LocoLearn" in Room Mars, 2nd floor, from 9:00. (Unfortunately I was not able to join this time, but my colleagues Davide Tateo and Piotr Kicki will!)

We are in the process of editing a SLAM handbook, to be published by Cambridge University Press, with many stellar contributors. Part 1 is available as an online draft for public comments. Help us find bugs/problems!

!! PhD Studentships - Please Retweet !! I have two funded studentships (to start October 25) in Oxford Robotics Institute Studentship 1 is in the space of multi-sensor mapping and scene understanding. I'm open to projects in scene graphs, neural representations and active mapping.

Have you wondered why I've posted all these nice plots and animations? 🤔 Well, the slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now! They cover quite a bit from basic information theory to some recent papers 🥳

🚨🚨 New #SLAM #RealityCapture Dataset! 🚨🚨 The Oxford Spires Dataset. New mapping benchmark in Oxford's famous colleges and Blenheim Palace focusing on high quality reconstruction (#nerf #gaussiansplatting) and colorization. dynamic.robots.ox.ac.uk/datasets/oxfor… #spatialai #oxford

EVER code release is out, you should use this. Quality is higher than 3DGS, it's mathematically impossible for renderings to "pop" (an extremely nice property, especially in VR applications), and it still renders in real-time.

Happy to share that I passed my DPhil viva last week! Huge thanks to my supervisor Maurice Fallon, my examiners Prof. Ayoung Kim and Prof. Victor Adrian Prisacariu, and my mentors and friends. I will continue as a PostDoc in Oxford Dynamic Robot Systems working on robot mapping and navigation.

Oxford Spires has been accepted to International Journal of Robotics Research (IJRR)! This dataset enables lidar-visual reconstruction with ground truth 3D maps and challenging sequences to test the robustness of outdoor NeRF/3DGS. dynamic.robots.ox.ac.uk/datasets/oxfor…

Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset Zirui Wang, Wenjing Bian, Xinghui Li, Ethan Yifu Tao, Jianeng Wang, Maurice Fallon, Victor Adrian Prisacariu tl;dr: egocentric dataset with GT 3D and lighting variation for benchmarking