Bruno Santos

@parskatt.bsky.social congrats for your PhD thesis submission and good luck to the defense

𝗛𝗔𝗠𝗦𝘁𝟯𝗥: 𝗛𝘂𝗺𝗮𝗻-𝗔𝘄𝗮𝗿𝗲 𝗠𝘂𝗹𝘁𝗶-𝘃𝗶𝗲𝘄 𝗦𝘁𝗲𝗿𝗲𝗼 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻
Sara Rojas, Matthieu Armando, Bernard Ghamen ... Gregory Rogez
arxiv.org/abs/2508.16433
Trending on www.scholar-inbox.com

Goodharts law

Climate change

I was wondering how education systems need to adapt to the advent of ChatGPT

Not intended like that

Elon would provide

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...

Congrats ! You are in a creative mode ! 3 papers in a row . Looking forward to read them

How does it compare with kitti dataset ?

FutureMapping: The Computational Structure of Spatial AI Systems We discuss and predict the evolution of Simultaneous Localisation and Mapping (SLAM) into a general geometric and semantic `Spatial AI' perception capability for intelligent embodied devices. A big ga...

Remember: the route to Spatial AI is through SLAM. Key research topics are representations for real-time fusion of measurements and priors into persistent semantic/metric scene models; and algorithm/hardware co-design for 1000X efficiency. #SpatialAI
arxiv.org/abs/1803.11288

Are you you depthanything v2 ?

Wang & all for the win

Yes . That was what I meant . Thanks

So one of downstream tasks is also tracking ? Can we separate from the other downstream tasks ?

Maybe less expensive than SF ?:’;)

😂😂😂

LeRobot goes to driving school: World’s largest open-source self-driving dataset We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Learning to Drive (L2D): the most exciting dataset release of the year by @hf.co & @yaak-ai.bsky.social
- 5K hours of driving data from 3 cameras
- lots of other synchronized data: GPU, IMU, CAN, actions, task descriptions
- 90TB of data
- LeRobot data formatting
huggingface.co/blog/lerobot...

Love it ♥️

This story reminds a bit how llms work nowadays. They output facts like the chofer .

We should have quotes peer review ;)

Congrats !!

Lots of jobs advertisements for computer vision require a PhD or bonus points for it . Is it s valid reason for doing it ?

How did you recover camera model without calibration?

Open source code now available MASt3R-SLAM: the best dense visual SLAM system I've ever seen. Real-time and monocular, and easy to run with a live camera or on videos without needing to know the camera calibration. Brilliant work from Eric and Riku.

Thanks !

Will the recording be available online ? Thanks

I learnt today about exploitation vs exploitation searching for new knowledge domains .

I will have to think more about this

That makes sense