Tomás Berriel Martins

Your #ICCV2025 paper got rejected? Give it another try and submit to our proceedings track!

Your #ICCV2025 paper got accepted? Congrats! Give it even more visibility by joining our nectar track.

More info: sites.google.com/view/neuslam...

More exciting news from @nianticspatial.bsky.social today. We've announced a partnership with Snap Inc. to build a next generation #AI map that will serve as the foundation for #AR glasses and AI agents to understand, navigate and interact with the real world.

YouTube video by SpAItial AI SpAItial AI: Building Spatial Foundation Models

🚀🚀🚀Announcing our $13M funding round to build the next generation of AI: 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 that can generate entire 3D environments anchored in space & time. 🚀🚀🚀

Interested? Join our world-class team:
🌍 spaitial.ai

youtu.be/FiGX82RUz8U

🚨 Just one month left to submit your solutions for The Structured Semantic 3D Reconstruction (S23DR-2025) Challenge!!! It is not too late to join!

Comp on @hf.co, part of the Workshop on Urban Scene Modeling at @cvprconference.bsky.social 2025

🔥$25,000 prize pool. Deadline: June 5, 2025.

🧵 (1/7)

I asked "on the other platform" what were the most important improvements to the original 2017 transformer.

That was quite popular and here is a synthesis of the responses:

RFK Jr wants us to believe that chronic illness is a moral failing. That people should “try harder” to be healthy.

He doesn’t want us to realize that poverty, food insecurity, lack of universal healthcare, poor public health and other government failures cause more disease than lifestyle ever will.

Why crash the economy? CONTROL.

Yarvin: "No, this is not the right way to run the whole economy permanently... But.. it is the right way to reboot the economy. Flattening the financial system this way makes it much easier to control crime, of course—and also, any kind of antigovernment activity."

🔍Looking for a multi-view depth method that just works?

We're excited to share MVSAnywhere, which we will present at #CVPR2025. MVSAnywhere produces sharp depths, generalizes and is robust to all kind of scenes, and it's scale agnostic.

More info:
nianticlabs.github.io/mvsanywhere/

NeurIPS participation in Europe We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

Sitting Andrew and Tristan Tate as guests of honor at a public event after they flew out of the country they were facing human trafficking charges in is rape culture in action

Huh. My research center in Teruel (Spain) offers up to two permanent positions for astrophysicists with 6+ years of postdoctoral experience, with this funding: www.araid.es/en/content/a...
Anybody interested in the J-PAS, J-PLUS, J-VAR surveys should contact clsj“_at_”cefca.es before February 14
🔭

New sharing step on our journey towards easy-to-use fully-open models.

Makes sense.

Has ChatGPT improved from just believing what the authors claim wo actually evaluating if the experiments support their claimed contributions?

I'm recruiting a new PhD student on Gaussian Belief Propagation for Spatial AI. For this particular opportunity: 1. The funding I have is only available to a student who qualifies for "home fees" in England; 2. I'm looking for someone who can start soon, ideally April 2025.

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)

Introducing MegaSaM!

Accurate, fast, & robust structure + camera estimation from casual monocular videos of dynamic scenes!

MegaSaM outputs camera parameters and consistent video depth, scaling to long videos with unconstrained camera paths and complex scene dynamics!

I would say around 200-300 papers. I'm not sure about attendees, but no more than 500 🤔

A young researcher in front of it's poster.

Just back from attending BMVC! Really interesting keynotes, and poster sessions. It was a great opportunities to meet new people and share ideas.
Unpopular opinion: like 3DV, it was definitely more enjoyable than the overcrowded CVPR 😅

Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread