Paul-Edouard Sarlin@pesarlin

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

 Zurich, Switzerland
psarlin.com/
Joined January 2019
79 Photos and videos
Honored and humbled to receive the ECVA PhD Award at #ECCV2026 @eccvconf! So grateful to my advisor @mapo1 for his guidance throughout, to all my brilliant coauthors over the years, and to the computer vision community for the support and the journey together. Thank you all
21
10
211
13,343
Excited to be at #ECCV2026 this week! Find me at ➡️ VidMap, a new system for 3D reconstruction from videos, poster #157 session #3 Thurs AM github.com/cvg/vidmap ➡️ ViLMa workshop Tuesday 8:45 for a talk covering VidMap and new works 🤫 vilma-workshop.github.io See you there 🤩
3
21
215
8,666
Paul-Edouard Sarlin retweeted
Zador Pataki@zador_pataki
Aug 7
Excited to share VidMap! #ECCV2026 We bring the temporal structure of SLAM into global SfM for accurate 3D reconstruction of long, unconstrained videos. 🚀 Code: github.com/cvg/vidmap 📄 Paper: arxiv.org/abs/2607.27194 🎥 Video: piped.video/gy4szd3q5Oo With @pesarlin & @mapo1
15
89
558
53,550
Paul-Edouard Sarlin retweeted
Kwang Moo Yi@kwangmoo_yi
Jul 30
Pataki et al., "VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion" SLAM uses temporal continuity but can drift; SfM can be out-of-order but ignores temporal continuity. In hindsight, we should obviously do both?
3
37
290
21,885
Paul-Edouard Sarlin retweeted
Zhenjun Zhao@zhenjun_zhao
Jul 30
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion @zador_pataki, @pesarlin, @mapo1 tl;dr: RoMa v2 + MFT + DAv3 + MegaLoc + different handling of sequential tracking and loop closure + metric-scale GLOMAP with depth priors arxiv.org/abs/2607.27194
20
119
17,749
Paul-Edouard Sarlin retweeted
Guillaume Astruc@g_astruc
Jun 23
🛰️ Introducing UniverSat: one transformer backbone for Earth Observation that handles ANY sensor, ANY spatial, spectral & temporal resolution, ANY scale — with a single set of weights. 🌍
4
46
309
24,002
Yes please! Open science FTW
Andrea Tagliasacchi@taiyasaki
Jun 7
📢📢📢 @CVPR motion proposal on best paper awards. Motion: Eligibility for Best Paper Awards shall require the public release of both source code and model weights.
1
44
7,922
Where is the code? No code, no public API, private datasets, too little details to reproduce = low impact. What does the award committee value?
#CVPR2026@CVPR
Jun 5
Announcing the official #CVPR2026 Best Paper Award Winner! 🏆 Congratulations to the authors for their landmark contributions to the field!👏👏
15
46
762
98,607
Paul-Edouard Sarlin retweeted
Dmytro Mishkin
@ducha_aiki
Jun 4
IMW 2026 -- @pesarlin started talk with @taiyasaki tweet :)
David Nordström@davnords
Jun 4
Matas kicking of goated IMW26 @CVPR, come listen to keynotes by e.g. @jianyuan_wang and @pesarlin. Will have a 10 minute talk about LoMa-R around 4pm. See you in 504
1
4
35
6,677
Excited to be at #CVPR2026 this week 🤩 Catch me for 3 workshop talks: ➡️ E2E 3D learning, Wed PM ➡️ Image matching, Thur PM Expect 🌶️ takes on learning/geometry and preview of new work. ➡️ EarthVision, Thur AM (+poster) about UniGeoCLIP, our latest work on geospatial learning.
1
32
1,936
Links: e2e3d.github.io/ image-matching-workshop.gith… grss-ieee.org/events/earthvi… Let's grab coffee if you're attending too! I'm really looking forward to catching up with old friends, my last CVPR was already 3 years ago.
6
956
Paul-Edouard Sarlin retweeted
Bharath Raj@bharathrajn98
May 28
Feed-forward 3D reconstruction methods typically predict pointmaps in camera-centric frames. But why should a camera's arbitrary orientation define the coordinate system? We introduce G3T, a transformer that predicts pointmaps in gravity-aligned frames. Regardless of input image orientation, our method always produces upright pointmaps (see demo). We leverage this uprightness to create G3T-Long, a submap-based reconstruction method that improves robustness on long-sequence 3D reconstruction (more on that below). Interactive demos, code, and model weights are available on our project page.
8
52
307
24,684
Paul-Edouard Sarlin retweeted
Linfei Pan@LinfeiPan
May 26
What if you could combine the precision of classical Structure-from-Motion with the local robustness of feedforward 3D models? Meet GLUEMAP — a CVPR 2026 highlight ✨ SOTA across 5 datasets spanning 6 challenges. w/ @ahojnnes & @mapo1 🌐website: lpanaf.github.io/cvpr26_glue…
1
22
94
7,969
Paul-Edouard Sarlin retweeted
Chris Offner
@chrisoffner3d
15 Oct 2025
Industry SLAM systems are far ahead of academic open source systems.
7
21
127
55,282
Camera pose estimation is solved when one controls the hardware and can afford multiple cameras/IMUs. Examples: Google StreetView, Meta Aria, robotics (IMUs are so cheap). Monocular SLAM (no IMU) isn’t solved but has limited practical relevance, mostly internet/historical videos.
Andrea Tagliasacchi@taiyasaki
May 13
This is why I refuse to work on camera estimation problems. For embodied AI, I consider it a **solved** problem at large – there are better things to spend your time on. It's only a "problem" in academia.
9
14
190
40,014
Paul-Edouard Sarlin retweeted
Zhiwen(Aaron) Fan
@zhiwen_fan_
Apr 18
End-to-End 3D Learning @ CVPR 2026. A workshop on moving from long 3D pipelines to trainable systems that map pixels or video directly to 3D. Keynote talks include digital humans, scene generation, mapping, end-to-end VLA, and SLAM. Paper deadline: May 1, 2026. Best Paper Award: $500 cash + certificate Best Demo Award: $500 cash + certificate Website + CFP: e2e3d.github.io/
11
99
13,222
Paul-Edouard Sarlin retweeted
Guillaume Astruc@g_astruc
Apr 16
Excited to share my work as a Student Researcher at Google Zurich: UniGeoCLIP! 🌍🚀 W/ Eduard Trulls, Jan Hosang, @loiclandrieu & @pesarlin, we built a framework aligning 5 geospatial modalities in one space. Presented at EarthVision @ #CVPR2026. 🧵👇
1
24
162
9,895
Paul-Edouard Sarlin retweeted
Chris Sweeney@the_shweenz
Apr 11
If only there were a benchmark for egocentric SLAM and VIO.... lamaria.ethz.ch/
FPV Labs
@fpv_labs
Apr 10
We are publishing our first deep dive on what we believe is one of the most challenging layers in egocentric data - SLAM and VIO in the context of long-horizon state tracking. We break down how SLAM and VIO fail in egocentric settings - visual features vanish at close range, depth sensors saturate, fast head motion blurs frames, and these failures don't always occur in isolation. They hit at the exact same moment, leading to compounding errors and making the downstream data unusable. We believe the foundation for high-quality egocentric data demands sub-centimeter precision over long episodes ranging from a few minutes to up to an hour.
1
6
82
12,645
Paul-Edouard Sarlin retweeted
Dmytro Mishkin
@ducha_aiki
Feb 9
RaCo: Ranking and Covariance for Practical Learned Keypoints Abhiram Shenoi @PhilippCSE @pesarlin @mapo1 tl;dr: ALIKED arch + DaD RL training with full 360deg rotaug with detector+covariance heads, separate ranker (sorter) model . No IMC eval #3DV2026 openreview.net/forum?id=BWtd…
2
15
60
7,745
There are papers that I love and could spend hours reviewing (like this one, which I unfortunately didn’t get assigned to in peer-review), and others that I would rather not read. I like the bidding system of NeurIPS but it has never worked for me, I always get random papers!
Dmytro Mishkin
@ducha_aiki
Jan 12
github.com/zju3dv/EfficientL… This is the depth of conversations between @pesarlin and Yifan Wang, one would dream to see in peer review. I'd dare to say, that is exactly peer review we want to have.
1
22
5,452
Load more