Frank Dellaert
@fdellaert.bsky.social
Robotics/Perception Prof at Georgia Tech; Chief AI Officer at Verdant Robotics. Stints at Skydio, B*8, Reality Labs, Google Research. https://dellaert.github.io
Reposted by Frank Dellaert
There are 2 previous historical cases of countries destroying their science and universities, crippling them for decades: Lysenkoism in the USSR and Nazi Germany. The Trump administration will be the 3rd.
It's not just budgets but research, institutions, expertise, and training the next generation.
It's not just budgets but research, institutions, expertise, and training the next generation.
May 31, 2025 at 4:43 AM
There are 2 previous historical cases of countries destroying their science and universities, crippling them for decades: Lysenkoism in the USSR and Nazi Germany. The Trump administration will be the 3rd.
It's not just budgets but research, institutions, expertise, and training the next generation.
It's not just budgets but research, institutions, expertise, and training the next generation.
GTSAM 4.3a0 ! github.com/borglab/gtsa...
Releases · borglab/gtsam
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse m...
github.com
May 21, 2025 at 3:00 PM
GTSAM 4.3a0 ! github.com/borglab/gtsa...
Reposted by Frank Dellaert
I know this look well. It’s the same one I get when I introduce the Fourier transform in my computer vision course to the CS crowd.
May 4, 2025 at 3:11 PM
I know this look well. It’s the same one I get when I introduce the Fourier transform in my computer vision course to the CS crowd.
Reposted by Frank Dellaert
Trump Says He Won’t Rule Out Third Reich
March 31, 2025 at 7:30 PM
Trump Says He Won’t Rule Out Third Reich
Part 2 of SLAM handbook is out for public comments! let us know what you think :-) Issue tracker on GitHub awaits! Link: github.com/SLAM-Handboo...
March 31, 2025 at 8:44 PM
Part 2 of SLAM handbook is out for public comments! let us know what you think :-) Issue tracker on GitHub awaits! Link: github.com/SLAM-Handboo...
Reposted by Frank Dellaert
And yet Joe Rogan puts guests on who say "Vaccines aren't actually responsible for the reduction in infectious diseases.”
March 30, 2025 at 5:30 PM
And yet Joe Rogan puts guests on who say "Vaccines aren't actually responsible for the reduction in infectious diseases.”
Reposted by Frank Dellaert
Aria Gen 2 is very impressive, with fully onboard SLAM and various other perception all within a 75g device with an hours-long battery life. Processing on custom silicon. Congrats to the Reality Labs team.
Introducing Aria Gen 2: Unlocking New Research in Machine Perception, Contextual AI, Robotics, and More
Today, we're excited to announce the next step in the Project Aria journey: the introduction of Aria Gen 2 research glasses.
www.meta.com
February 28, 2025 at 5:10 PM
Aria Gen 2 is very impressive, with fully onboard SLAM and various other perception all within a 75g device with an hours-long battery life. Processing on custom silicon. Congrats to the Reality Labs team.
Reposted by Frank Dellaert
MASt3R-SLAM code release!
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation.
Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.
With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.
With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
February 25, 2025 at 5:23 PM
MASt3R-SLAM code release!
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
Reposted by Frank Dellaert
CRA statement about NSF firings cra.org/cuts-to-nsf-...
Cuts to NSF and CISE Directorate Jeopardize American Leadership in Computing
A statement from the Computing Research Association (CRA) The reported termination today of 10 percent of the National Science Foundation’s (NSF) workforce — including significant cuts to the Compu…
cra.org
February 18, 2025 at 11:52 PM
CRA statement about NSF firings cra.org/cuts-to-nsf-...
Some personal news: as of January I am back full-time at Georgia Tech following a 2-year leave as Verdant Robotics’ CTO. I will continue to be involved with Verdant as part-time Chief AI Officer, thinking strategically about the role of AI in Robotics for Ag.
February 18, 2025 at 10:11 PM
Some personal news: as of January I am back full-time at Georgia Tech following a 2-year leave as Verdant Robotics’ CTO. I will continue to be involved with Verdant as part-time Chief AI Officer, thinking strategically about the role of AI in Robotics for Ag.
Gemini is good but too verbose :-)
February 12, 2025 at 8:01 PM
Gemini is good but too verbose :-)
The visual system of a jumping spider is fascinating. Look at those cones behind the fixed main lenses! The retinas are at the end of the cones. youtu.be/gvN_ex95IcE?...
Yellow amycine jumping spider, Reserva Canadé, Ecuador
YouTube video by wmaddisn
youtu.be
February 9, 2025 at 5:33 PM
The visual system of a jumping spider is fascinating. Look at those cones behind the fixed main lenses! The retinas are at the end of the cones. youtu.be/gvN_ex95IcE?...
Reposted by Frank Dellaert
We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
February 6, 2025 at 6:34 PM
We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.
Reposted by Frank Dellaert
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
TL;DR: Long videos support; Depth Anything
V2 with efficient spatial-temporal head. Temporal
consistency loss -> depth gradient (no geometric priors)
TL;DR: Long videos support; Depth Anything
V2 with efficient spatial-temporal head. Temporal
consistency loss -> depth gradient (no geometric priors)
January 22, 2025 at 1:22 PM
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
TL;DR: Long videos support; Depth Anything
V2 with efficient spatial-temporal head. Temporal
consistency loss -> depth gradient (no geometric priors)
TL;DR: Long videos support; Depth Anything
V2 with efficient spatial-temporal head. Temporal
consistency loss -> depth gradient (no geometric priors)
Maybe a broom attached to the train :-)
January 21, 2025 at 10:05 PM
Maybe a broom attached to the train :-)
That’s such a cool idea! (Thanks K for flagging this to me)
Solar panels are becoming so cheap the Swiss are looking at installing them *between train tracks* !!!
www.pv-magazine.com/2024/10/04/s...
www.pv-magazine.com/2024/10/04/s...
January 21, 2025 at 8:01 PM
That’s such a cool idea! (Thanks K for flagging this to me)
Not sure I’m optimistic about that :-) I can see the number of humans involved decrease. Georgia Techs OMSCS is a good metaphor. More TAs, less teachers. TAs will be replaced by AI: one AI-TA per student per course.
January 12, 2025 at 8:51 PM
Not sure I’m optimistic about that :-) I can see the number of humans involved decrease. Georgia Techs OMSCS is a good metaphor. More TAs, less teachers. TAs will be replaced by AI: one AI-TA per student per course.
I’m sure oxbridge tutors have a pretty good idea of what they have in front of them after a couple of sessions :-)
January 12, 2025 at 8:47 PM
I’m sure oxbridge tutors have a pretty good idea of what they have in front of them after a couple of sessions :-)
I don’t have the answers. But I’m optimistic we’ll arrive at a good outcome eventually. We will still need to find a way to somehow contribute value, and to document that fact in order to get hired for those skills. Maybe the key to certification lies in those 1-1 tutoring sessions themselves.
January 12, 2025 at 8:46 PM
I don’t have the answers. But I’m optimistic we’ll arrive at a good outcome eventually. We will still need to find a way to somehow contribute value, and to document that fact in order to get hired for those skills. Maybe the key to certification lies in those 1-1 tutoring sessions themselves.
Sure. I think we’ll have to find a different way. At this point when I code, I use ChatGPT/Claude extensively, so maybe we should start thinking about this being a valid way to complete assignments :-)
January 12, 2025 at 8:39 PM
Sure. I think we’ll have to find a different way. At this point when I code, I use ChatGPT/Claude extensively, so maybe we should start thinking about this being a valid way to complete assignments :-)
I am more optimistic. It’s well known that one on one tutoring can be up to two standard deviations more effective than classroom teaching, but it’s prohibitively expensive. AI gives us cost-effective solution for just that. It’s *already* doing that for me :-)
January 12, 2025 at 7:55 PM
I am more optimistic. It’s well known that one on one tutoring can be up to two standard deviations more effective than classroom teaching, but it’s prohibitively expensive. AI gives us cost-effective solution for just that. It’s *already* doing that for me :-)