PhD student in the Computer Vision and Geometry Group, ETH Zürich
Zurich, Switzerland
Joined October 2013
- Tweets29
- Following249
- Followers387
- Likes274
Philipp Lindenberger retweeted
FlexGlue: Sparse-to-Dense Feature Matching and Visual Disambiguation
@PhilippCSE @pesarlin Ondrej Miksik @mapo1
tl;dr: transformer for dinov3 token matching, then query with anything (grid, keypoints) and image overlap clf.
Trained with negatives!
arxiv.org/abs/2610.32976
Philipp Lindenberger retweeted
VisMatch v1.4.0 is out, with RaCo, UPAL, and REDI-Match!
5 lines of code to try 50+ image matchers
To match or not to match?
FlexGlue 🐙, our new image-matching model, can match every pixel AND reject doppelganger pairs, tackling a common failure case in SfM.
➡️State-of-the-art SfM and matching, blazing fast
➡️Code: github.com/cvg/FlexGlue
➡️Paper: arxiv.org/pdf/2610.32976
1/
➡️Through data augmentation, FlexGlue is also robust to in-plane rotations, especially when paired with the RaCo keypoint detector by @shenbuoy.
github.com/cvg/RaCo
7/
This was an amazing collaboration between @cvg_ethz , @Google and @Microsoft with @pesarlin, Ondrej Miksik, and @mapo1. We also want to thank @mihaidusmanu who helped a lot in the initial phase of the project.
8/8
Philipp Lindenberger retweeted
The submissions to our @CVPR workshop OpenSUN3D on Open-World 3D Scene Understanding and Representations are open! 🏔️🤖☀️
➡️ The deadline for the proceedings track is on the 5th of March!🏃♀️
🌍: opensun3d.github.io
📝: openreview.net/group?id=thec…
Philipp Lindenberger retweeted
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…
At #NeurIPS2025, we're presenting our work on Scaling Image Geo-Localization to Continent Level.
Website: scaling-geoloc.github.io
Paper: arxiv.org/pdf/2510.26795.pdf
If you are at the conference, say 👋:
📍 Poster #4812, Dec 3 (Wed), 4:30–7:30 PM PST
Philipp Lindenberger retweeted
Some benchmark of the modern local features with LightGlue on #IMC2021 dataset.
0) Use ALIKED features.
1) ALIKED 2k is on par with other features 8k
2) DISK overfits to buildings
3) DoG detector benefits from 8k the most
Philipp Lindenberger retweeted
📢Join us tomorrow Friday morning at our #ICCV2023 poster S-6 to learn more about LightGlue!
💥We have released the training code at github.com/cvg/glue-factory
➡️You can now train LightGlue with SIFT, ALIKED, or your own local features, on your own dataset
⏩More models coming soon!
You liked SuperGlue? You'll love ⚡️LightGlue⚡️, our new deep network for light-speed image matching!
➡️Faster, stronger, easier to train than SuperGlue
➡️Code: github.com/cvg/LightGlue
➡️Paper: arxiv.org/pdf/2306.13643.pdf
Fantastic work by @PhilippCSE for #ICCV2023, with @mapo1
1/
Philipp Lindenberger retweeted
You liked SuperGlue? You'll love ⚡️LightGlue⚡️, our new deep network for light-speed image matching!
➡️Faster, stronger, easier to train than SuperGlue
➡️Code: github.com/cvg/LightGlue
➡️Paper: arxiv.org/pdf/2306.13643.pdf
Fantastic work by @PhilippCSE for #ICCV2023, with @mapo1
1/
Philipp Lindenberger retweeted
Best Student Paper @ICCV_2021
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement
Philipp Lindenberger (ETH Zurich), Paul-Edouard Sarlin (ETH Zurich), Viktor Larsson, Marc Pollefeys
[Session 5 A/B]
Philipp Lindenberger retweeted
🚨 This week at #ICCV2021, check out "Pixel-Perfect Structure-from-Motion with Featuremetric Refinement" w/ @PhilippCSE V. Larsson @mapo1
➡️ oral & *best student paper award*
Website: psarlin.com/pixsfm
Paper: arxiv.org/abs/2108.08291
Video: youtu.be/2HuCMuraFk0
thread ⬇️