iiinova — where your digital self keeps evolving

Eric Dexheimer

@ericdexheimer.bsky.social

199 followers 123 following 5 posts

PhD student at Dyson Robotics Lab, Imperial College London edexheim.github.io

Posts Replies Media

Reposted by Eric Dexheimer

Christian Wolf @chriswolfvision.bsky.social · 29/07/2025

Naver Labs Europe organizes a Workshop on AI for Robotics in the French Alpes (Grenoble), the 4th edition. This year the topic is 'Spatial AI', registration is open!

0164

Reposted by Eric Dexheimer

Sergio Izquierdo @sizquierdo.bsky.social · 31/03/2025

🔍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/

23910

Eric Dexheimer @ericdexheimer.bsky.social · 11/03/2025

Cool work! Do you think there’s any architectural bias that prevents learning extrema rather than only minima or only maxima? Or is it mostly the repeatability issue? Just has me thinking about classical SIFT DoG and Harris handling both light/dark

110

Eric Dexheimer @ericdexheimer.bsky.social · 25/02/2025

This is a fun example with a continuous transition between distinct 3D scenes!

090

Eric Dexheimer @ericdexheimer.bsky.social · 25/02/2025

Here's a reconstruction of a movie establishing shot

1110

Eric Dexheimer @ericdexheimer.bsky.social · 25/02/2025

We’ve had fun testing the limits of MASt3R-SLAM on in-the-wild videos. Here’s the drone video of a Minnesota bowling alley that we’ve always wanted to reconstruct! Different scene scales, dynamic objects, specular surfaces, and fast motion.

3455

Eric Dexheimer @ericdexheimer.bsky.social · 13/01/2025

I’m not too familiar with it, but it seems there is some equivalence noted in Section 3.2 of “Feature preserving point set surfaces based on non‐linear kernel regression”.

030

Reposted by Eric Dexheimer

Riku Murai @rmurai0610.bsky.social · 16/12/2024

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)

510016