Paul-Edouard Sarlin @pesarlin.bsky.social (@pesarlin) 's Twitter Profile
Paul-Edouard Sarlin @pesarlin.bsky.social

@pesarlin

Researcher at @Google, 3D computer vision & machine learning. Previously PhD at ETH Zurich, intern at @Google, @Meta, @Microsoft, @magicleap. Now on Bluesky 🦋

ID: 1084742570264150016

linkhttps://psarlin.com/ calendar_today14-01-2019 09:22:37

380 Tweet

5,5K Followers

470 Following

Benjamin Azoulay (@b_azoulay) 's Twitter Profile Photo

🎄Connaissez-vous cet intérieur de Noël par Vermeer ? Et ce sapin tahitien de Gauguin ? Depuis un an je développe une IA qui permet à tous de créer des images à la manière de peintres célèbres à partir d’un dessin d’une photo ou d’une description👉babelgallery.com/drawing

🎄Connaissez-vous cet intérieur de Noël par Vermeer ? Et ce sapin tahitien de Gauguin ? Depuis un an je développe une IA qui permet à tous de créer des images à la manière de peintres célèbres à partir d’un dessin d’une photo ou d’une description👉babelgallery.com/drawing
Dmytro Mishkin 🇺🇦 (@ducha_aiki) 's Twitter Profile Photo

MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion Zador Pataki Paul-Edouard Sarlin , Johannes L. Schonberger, Marc Pollefeys tl;dr: using monodepth to reconstruct w/o co-visible triplets. Many ablations and details. M3Dv2 FTW demuc.de/papers/pataki2…

MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion

<a href="/zador_pataki/">Zador Pataki</a>  <a href="/pesarlin/">Paul-Edouard Sarlin</a> , Johannes L. Schonberger, <a href="/mapo1/">Marc Pollefeys</a> 
tl;dr: using monodepth to reconstruct w/o co-visible triplets. Many ablations and details. M3Dv2 FTW
demuc.de/papers/pataki2…
Kwang Moo Yi (@kwangmoo_yi) 's Twitter Profile Photo

Paper of today: Pataki et al., "MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion" -- github.com/cvg/mpsfm Depth estimators work great. Time to integrate them into SfM pipelines.

Zador Pataki (@zador_pataki) 's Twitter Profile Photo

Excited to share the first paper of my PhD: MP-SfM! #CVPR2025 We augment SfM with monocular depth & normals to handle extreme low-overlap scenes. 🚀 Code: github.com/cvg/mpsfm 📄 Paper: arxiv.org/pdf/2504.20040 Exciting collaboration with Paul-Edouard Sarlin @pesarlin.bsky.social, J.L. Schönberger & Marc Pollefeys

Paul-Edouard Sarlin @pesarlin.bsky.social (@pesarlin) 's Twitter Profile Photo

Don’t miss the chance to learn more about our latest Structure-from-Motion system leveraging monocular depth & normal priors at #CVPR2025 ➡️ Poster 80, session 5, Sunday (tomorrow!) 10:30 ➡️ Code: github.com/cvg/mpsfm Congratulations to Zador for the great work! 🙌

Paul-Edouard Sarlin @pesarlin.bsky.social (@pesarlin) 's Twitter Profile Photo

We released COLMAP v3.12, which adds long-awaited end-to-end support for multi-camera rigs and 360° panoramas 👀 COLMAP just got better at handling your robotics, AR/VR, or 360 data - try it and let us know! github.com/colmap/colmap/… Kudos to Johannes & team for this great work 🚀

We released COLMAP v3.12, which adds long-awaited end-to-end support for multi-camera rigs and 360° panoramas 👀 COLMAP just got better at handling your robotics, AR/VR, or 360 data - try it and let us know! github.com/colmap/colmap/… Kudos to Johannes &amp; team for this great work 🚀
Paul-Edouard Sarlin @pesarlin.bsky.social (@pesarlin) 's Twitter Profile Photo

Of course we welcome feature requests and community contributions! We have a long roadmap and certainly could use some help - please do reach out if you have relevant experience and time to spare for an amazing open-source impact 😀

Dmytro Mishkin 🇺🇦 (@ducha_aiki) 's Twitter Profile Photo

Welcome to 50th Pattern Recognition and Computer Vision Colloquium with: - Torsten Sattler - Paul-Edouard Sarlin - Vicky Kalogeiton - Spyros Gidaris - Anna Kukleva - Lukas Neumann Thursday Oct 9, 11:00-17:00. You still have time to buy tickets to Prague! cmp.felk.cvut.cz/colloquium/

Welcome to 50th Pattern Recognition and Computer Vision Colloquium with:
- <a href="/SattlerTorsten/">Torsten Sattler</a> 
- <a href="/pesarlin/">Paul-Edouard Sarlin</a> 
- <a href="/VickyKalogeiton/">Vicky Kalogeiton</a>  
- Spyros Gidaris
-  <a href="/anna_kukleva_/">Anna Kukleva</a>  
- <a href="/lukneu/">Lukas Neumann</a>
Thursday Oct 9, 11:00-17:00.   
You still have time to buy tickets to Prague!
cmp.felk.cvut.cz/colloquium/
Andrew Davison (@ajddavison) 's Twitter Profile Photo

A reminder that accurate motion estimation sparse visual SLAM has been in the domain of industry for many years now, and what you might often see in academic papers as the "state of the art" is fairly meaningless. (From Paul-Edouard Sarlin @pesarlin.bsky.social.bsky.social)

CVG (@cvg_ethz) 's Twitter Profile Photo

#ICCV2025 is starting today 🌺 you can find us at: 🥽 LaMAria Tutorial: 325B, 1:00PM ➡️lamaria.ethz.ch/tutorial ☀️ OpenSUN3D Workshop: 306 B, 1:30PM ➡️opensun3d.github.io Paul-Edouard Sarlin Elisabetta Fedele Francis Engelmann Alex Delitzas Marc Pollefeys #ICCV2025

#ICCV2025 is starting today 🌺 you can find us at:  

🥽 LaMAria Tutorial: 325B, 1:00PM  
➡️lamaria.ethz.ch/tutorial 

☀️ OpenSUN3D Workshop: 306 B, 1:30PM 
➡️opensun3d.github.io

<a href="/pesarlin/">Paul-Edouard Sarlin</a> <a href="/efedele16/">Elisabetta Fedele</a> <a href="/FrancisEngelman/">Francis Engelmann</a> <a href="/AlexDelitzas/">Alex Delitzas</a>  <a href="/mapo1/">Marc Pollefeys</a> <a href="/ICCVConference/">#ICCV2025</a>