Patrick Wenzel

AI Research Engineer @ Helsing. Research on computer vision and deep learning. Previously PhD @TU_Muenchen and intern @NianticLabs and @Meta @RealityLabs.

[Heng Yang @hankyang94]

"Building Rome with Convex Optimization" has been accepted to #RSS2025!

Try XM, our new structure from motion pipeline powered by GPU-accelerated convex semidefinite optimization:
https://t.co/ygjltwNzH4

XM solves large-scale (nonconvex) global bundle adjustment problem via learned depth and a tight convex semidefinite relaxation.

By implementing the Burer-Monteiro low-rank factorization algorithm in CUDA, XM can solve bundle adjustment problems with more than 10,000 images/views.

Technical details in the paper: https://t.co/BuF6y7bqZ3

Kudos to @Hyhan0118

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Unanswered research questions in Image Matching

[Jon Barron @jon_barron]

One reason generative 3D is hard is that the world has barely any 3D training data. Today, most humans on earth will snap a few photos and write paragraphs of text. In contrast, earth has maybe ~50k 3D artists, and each will make maybe ~1k photoreal 3D models over their career.

[Eric Dexheimer @eric_dexheimer]

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.

[Riku Murai @rmurai0610]

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 @eric_dexheimer*, @AjdDavison (*Equal Contribution)

[Andrew Davison @AjdDavison]

Devil's advocate mode on: Navigation World Models have existed for a long time... they're called maps! And there are plenty of good algorithms out there which enable robots to build them / render views from them / localise within them / use them for planning. #SLAM #SpatialAI :)

[Patrick Wenzel @PatrickWenzelML]

I’ll be at the conference tomorrow and on Friday. PM me if you’d like to chat about what we are doing!

[Cédric Archambeau 🇺🇦🇪🇺🦋 @cedapprox]

I will be joining @corl_conf community tomorrow. https://t.co/ctEC4h84v3 will be hosting an event on Thursday. Stop by our booth if you’d like to know more about what we do and how how work contributes to defending our liberal democracies !

[Tsarathustra @tsarnick]

Mark Zuckerberg on Meta's open source AI strategy: "We're not doing this because we're altruistic... I don't view it as giving it away, I view it as you guys all making it better for me"

[Kyunghyun Cho @kchonyc]

very cool to see a pretty exhaustive and extensive technical report on llama-3.1!

a few fun snippets 🧵

[Amar Ali-bey @amaralibey]

🚀 Excited to release OpenVPRLab! 🎉
An open-source framework for Visual Place Recognition (VPR), featuring extensible, modular, and scalable components, enabling researchers to train/develop deep VPR models with reproducible SOTA performance.

🔗https://t.co/2pWkiGwzIq

🧵👇

[Patrick Wenzel @PatrickWenzelML]

DMs are open now!

[Patrick Wenzel @PatrickWenzelML]

We’re looking for computer vision and machine learning PhD interns to join our team.

It’s a great opportunity to work on challenging and cutting-edge computer vision and machine learning problems!

I’ll be at #CVPR this week. PM me!

https://t.co/CifY8s2kAf

[Patrick Wenzel @PatrickWenzelML]

What a great community. We had a full house yesterday and a great lineup of keynote speakers!

We had stimulating discussions and a really exciting panel! We hope everyone enjoyed it!

Thanks to all the speakers and to the organizers who contributed to the success of the event!

[Patrick Wenzel @PatrickWenzelML]

Make sure to join us for the Visual Localization and Mapping Workshop (ViLMa) on Monday morning @CVPR!

We have an outstanding lineup of keynote speakers:
@smash0190 @lukasvst @VincentLepetit2 @jajuengel Peter Kontschieder @lealtaixe @mapo1

More details: https://t.co/5SuQ2XDlCQ

[Patrick Wenzel @PatrickWenzelML]

@valzadrija @CVPR @smash0190 @lukasvst @VincentLepetit2 @jajuengel @lealtaixe @mapo1 The recording will be available on YouTube after approximately 3 months.

[Patrick Wenzel @PatrickWenzelML]

Make sure to join us for the Visual Localization and Mapping Workshop (ViLMa) on Monday morning @CVPR!

We have an outstanding lineup of keynote speakers:
@smash0190 @lukasvst @VincentLepetit2 @jajuengel Peter Kontschieder @lealtaixe @mapo1

More details: https://t.co/5SuQ2XDlCQ

[TimDarcet @TimDarcet]

With satellite imagery, it’s hard to get labels. Solution? DINOv2!
WRI+Meta trained a satellite DINOv2 for tree height estimation. They created an interactive map of tree height of the whole globe (!) at 1-meter res (!): https://t.co/W2kVEonvzR
Quizz: Can you recognize this city?

[MrNeRF @janusch_patas]

Lecture recordings from MIT about inverse rendering. Teaches also some Gaussian Splatting basics for free! https://t.co/YTXJ14oFp4
Credits go to @cs_mshah for bringing it to my attention #3DGS

[Jürgen Schmidhuber @SchmidhuberAI]

The GOAT of tennis @DjokerNole said: "35 is the new 25.” I say: “60 is the new 35.” AI research has kept me strong and healthy. AI could work wonders for you, too!

[Patrick Wenzel @PatrickWenzelML]

Super excited to announce that our workshop ViLMa - Visual Localization and Mapping has been accepted at @CVPR. Please stay tuned for more updates & see you all in Seattle!

[Patrick Wenzel @PatrickWenzelML]

Helsing is hiring 2024 PhD interns in the area of 3D computer vision, machine learning, and generative AI.

See intern call below for more details.
https://t.co/PacbNnwHFr