Amy Tabb

Hello computer vision people! I've been over at Mastodon for 2 years, and felt out of the loop -- happy to see the crowd over here. Thanks folks for the starter packs! Photo: Inca the Rottweiler at home. Nikon z6ii, f/1.8, 1/250s, ISO 2000, 50mm, handheld.

Image Matching Challenge 2026. It is named "IMC 2025 On-going". - It will be living for longer than "until next CVPR" - multiyear leaderboard. - No prize, but invite to talk about solution at CVPR. - Dataset+metrics same as 2025. www.kaggle.com/competitions... #CVPR2026 @cvprconference.bsky.social

You still have 2 weeks to submit your paper to Image Matching Workshop at #CVPR2026 Deadline: March 16. Topics: anything related to image matching and 3D reconstruction. cmt3.research.microsoft.com/IMW2026 @cvprconference.bsky.social

Submit your paper of structured reconstruction -- CAD, semantic, wireframe, city monitoring, etc., to USM3D 2026! cmt3.research.microsoft.com/USM2026 Deadline: March 24, 2026. @cvprconference.bsky.social #CVPR2026 #USM3D2026 #USM3D

[reading rec] The Orphan Master's Son, by Adam Johnson, 2012. ISBN 978-0812992793. Set in N Korea, an orphan -- who may not be an orphan! -- makes his way in a difficult world. Themes of propaganda and creation of conflicting constraints on thinking & behavior. Reality and identity.

Secret to a successful research career: 1. Get super lucky and have the stars align for your first year 2. Repeat ~40 times 3. Retire

I finished reading Enriquez's _A Sunny Place for Shady People_. I had a tough time getting into the earlier stories in the collection but loved the later ones. Next, I am looking for the Enriquez's other short story collection, _The Dangers of Smoking in Bed_.

‘My Work Doesn’t Define Me,’ Says Man Who Will Spend 90,000 Hours Of Lifetime At Office

My wonderfully weird children are back in school as of today, ahhhh quiet again 🫠

One of my PhD students got their visa revoked. I know of other cases amongst my AI colleagues. This is not what investing in US leadership in AI looks like. www.aljazeera.com/news/2025/4/...

VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets Alejandro Fontan, Tobias Fischer, Javier Civera, Michael Milford tl;dr: arxiv.org/abs/2504.04457

The AI for Science summer school, coorganized by CNRS and U of Chicago will be in Paris, June 30th to july 4th, register asap if you want attend! datascience.uchicago.edu/events/ai-sc...

Mrs. Blackbird looking for nesting material. Have a great day☕🖖 #Amsel #blackbird 📷 🌿 🪶 🐦 #Nikon #Fotografie #naturephotography #photography #birds #wildlife

One of the perfect da share zone memes 🤌

Just received the first volume, and damn, clearly a ton of effort was put into it! There's a ~90 page intro to "foundations of complexity science" (which is also sold separately). (The super interesting) papers each have a 5-10 page intro with historical context, and are full of annotations ❤️

MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion Zador Pataki, @pesarlin.bsky.social Johannes L. Schonberger, @marcpollefeys.bsky.social tl;dr: using monodepth to reconstruct w/o co-visible triplets. Many ablations and details. M3Dv2 FTW demuc.de/papers/patak...

🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷 Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa... Big 🧵👇 with details!

Welcome to our world Riona! We lost Inca the Rottweiler at 8 years old about a month ago. It didn't feel right, to be at home with no dog, and I missed inca terribly. We found Riona the Rottweiler at an SPCA and she is a gem. Nikon z6ii, f/1.8, 1/400s, ISO4000, 50mm, handheld.

Fixing the RANSAC Stopping Criterion Johannes Schönberger, Viktor Larsson, @marcpollefeys.bsky.social tl;dr: ratio between the number of all-inlier samples and the number of possible samples->fix the approximate probability in RANSAC arxiv.org/abs/2503.07829

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration Javier Tirado-Garín, Javier Civera tl;dr: FOV field parameterization >> Perspective field. Sota on focal length estimation arxiv.org/abs/2503.12701

A Framework for Reducing the Complexity of Geometric Vision Problems and its Application to Two-View Triangulation with Approximation Bounds Felix Rydell @bokmangeorg.bsky.social @fredkahl.bsky.social Kathlén Kohn tl;dr:cool for triangulation,won't pretend I got the math arxiv.org/abs/2503.08142

8-Calves Image dataset Xuyang Fang, Sion Hannuna, Neill Campbell tl;dr: 1 hour video of 8 calves. + some object detector & classifier eval arxiv.org/abs/2503.13777

This morning I woke up at 6 to spend some time in Jurong before going to work. Hoping to finally find the black bittern... Well, the bittern remained hidden, but hornbills came and said hello!

This has only been possible through NIH funding. Funding biomedical science through the NIH has been one of the greatest accomplishments of the United States of America for America, and for the world. We are ALL better for the work that passionate scientists funded by the NIH have been able to do.

I am so angry about what is happening in the US, and to Columbia University students. The US government are entrapping students, lying about them, upending their whole lives. "The department [of Homeland Security] did not provide any evidence for its allegations." www.nytimes.com/2025/03/15/n...

Excellent post from (my former😢 colleague) Nicholas Carlini on the differences between copyright law & privacy research. In particular, from a privacy perspective, "was training data memorized?" is a yes/no question; we aren't trying to quantify how much data was memorized beyond "some" vs "none".

Trump: COLUMBA IS AWFUL Columbia: [slaps student] Trump: COLUMBIA IS ANTISEMITIC Columbia: [kicks student in groin] Trump: NO MONEY FOR COLUMBIA LOL Columbia: [punches brown student in nose] Trump: WE WILL CLOSE COLUMBIA Columbia: [reaching for another student] okay this time it will work